> This is a page from the ElevenLabs documentation. For a complete page index, fetch https://elevenlabs.io/docs/llms.txt. For the full documentation in a single file, fetch https://elevenlabs.io/docs/llms-full.txt.

# Skapa transkript

POST https://api.elevenlabs.io/v1/speech-to-text
Content-Type: multipart/form-data

Transkribera en ljud- eller videofil. Om webhook är satt till true behandlas begäran asynkront och resultaten skickas till konfigurerade webhooks. När use_multi_channel är true och det angivna ljudet har flera kanaler returneras ett 'transcripts'-objekt med separata transkriptioner för varje kanal. Sätt multichannel_output_style='combined' för att i stället få en enda transkription där alla kanaler har slagits samman och sorterats efter tid. Annars returneras en enda transkription. Den valfria parametern webhook_metadata låter dig bifoga anpassade data som inkluderas i webhook-svar för att koppla och spåra begäranden.

Reference: https://elevenlabs.io/docs/api-reference/speech-to-text/convert

## Servers

- `https://api.elevenlabs.io` (Production, default)
- `https://api.us.elevenlabs.io` (Production US)
- `https://api.eu.residency.elevenlabs.io` (Production EU)
- `https://api.in.residency.elevenlabs.io` (Production India)
- `https://api.sg.residency.elevenlabs.io` (Production Singapore)

## Request

### Query parameters

- `token` (string, optional, nullable) — En autentiseringstoken för engångsbruk som skapas via POST /v1/single-use-token/batch_scribe. Den här tokenen kan bara användas en gång och upphör att gälla efter 15 minuter. Ett alternativ till API-nyckel eller autentisering med bearer-token för frontendklienter.
- `enable_logging` (boolean, optional, default: true) — När enable_logging är satt till false används nollkvarhållningsläge för begäran. Det innebär att lagringsfunktioner för loggar och transkript inte är tillgängliga för denna begäran. Nollkvarhållningsläge får endast användas av företagskunder.

### Body (multipart/form-data)

This endpoint expects a multipart form containing an optional file.

- `model_id` (string, required) — ID:t för modellen som ska användas för transkribering.
- `file` (file, optional) — Filen som ska transkriberas (minsta ljudlängd är 100 ms). Alla vanliga ljud- och videoformat stöds. Exakt en av parametrarna file eller cloud_storage_url måste anges. Filstorleken måste vara mindre än 5,0 GB.
- `language_code` (string, optional) — En ISO-639-1- eller ISO-639-3-language_code som motsvarar ljudfilens språk. Kan ibland förbättra transkriberingsprestandan om språket är känt i förväg. Standardvärdet är null, och då förutsägs språket automatiskt.
- `transcript_edit` (string, optional) — Instruktion på naturligt språk som tillämpas på den slutliga transkriptionen (max 2 000 tecken). Den redigerade texten returneras i 'edited_transcript' tillsammans med originaltranskriptionen. Kan inte kombineras med entity_detection, entity_redaction eller use_multi_channel. Användning av den här parametern medför ett tillägg på 30 % av grundkostnaden för transkribering, debiterat för minst 10 sekunders ljud.
- `tag_audio_events` (boolean, optional) — Om ljudhändelser som (skratt), (fotsteg) osv. ska taggas i transkriberingen.
- `num_speakers` (integer, optional) — Det högsta antalet talare i den uppladdade filen. Kan hjälpa till att förutsäga vem som talar när. Högst 32 talare kan förutsägas. Standardvärdet är null; då sätts antalet talare till det högsta värde som modellen har stöd för.
- `timestamps_granularity` (enum, optional) — Detaljnivån för tidsstämplarna i transkriberingen. 'word' ger tidsstämplar på ordnivå och 'character' ger tidsstämplar på teckennivå för varje ord.
- `diarize` (boolean, optional) — Om det ska markeras vilken talare som för närvarande talar i den uppladdade filen.
- `diarization_threshold` (double, optional) — Diariseringströskel som används vid talardiarisering. Ett högre värde innebär lägre risk att en talare diariseras som två olika talare, men högre risk att två olika talare diariseras som en talare (färre talare förutsägs totalt). Ett lågt värde innebär högre risk att en talare diariseras som två olika talare, men lägre risk att två olika talare diariseras som en talare (fler talare förutsägs totalt). Kan endast anges när diarize=True och num_speakers=None. Standardvärdet är None, och då väljer vi en tröskel baserat på model_id (vanligtvis 0.22).
- `additional_formats` (list of ExportOptions, optional) — En lista över ytterligare format att exportera transkriptionen till.
- `file_format` (enum, optional) — The format of input audio. Options are 'pcm_s16le_16' or 'other' For `pcm_s16le_16`, the input audio must be 16-bit PCM at a 16kHz sample rate, single channel (mono), and little-endian byte order. Latency will be lower than with passing an encoded waveform.
- `cloud_storage_url` (string, optional) — [Föråldrat] Den här parametern är föråldrad och kommer att tas bort i framtiden. Använd 'source_url' i stället. HTTPS-URL:en för filen som ska transkriberas. Exakt en av parametrarna file eller cloud_storage_url måste anges. Filen måste vara tillgänglig via HTTPS och vara mindre än 2 GB. Alla giltiga HTTPS-URL:er accepteras, inklusive URL:er från molnlagringsleverantörer (AWS S3, Google Cloud Storage, Cloudflare R2 osv.), CDN:er eller andra HTTPS-källor. URL:er kan vara försigneda eller innehålla autentiseringstoken i frågeparametrar.
- `source_url` (string, optional) — Webbadressen till en ljud- eller videofil som ska transkriberas. Stöder lagrade video- eller ljudfiler, YouTube-video-URL:er, TikTok-video-URL:er och andra videohostingtjänster.
- `webhook` (boolean, optional) — Om transkriberingsresultatet ska skickas till konfigurerade speech-to-text-webhooks. Om detta anges returneras begäran tidigt utan transkriberingen, som levereras senare via webhook.
- `webhook_id` (string, optional) — Valfritt specifikt webhook-ID att skicka transkriptionsresultatet till. Gäller endast när webhook är satt till true. Om det inte anges skickas transkriptionen till alla konfigurerade speech-to-text-webhooks.
- `temperature` (double, optional) — Styr slumpmässigheten i transkriberingsresultatet. Accepterar värden mellan 0.0 och 2.0, där högre värden ger mer varierade och mindre deterministiska resultat. Om värdet utelämnas använder vi en temperatur baserad på den modell du har valt, vilket vanligtvis är 0.
- `seed` (integer, optional) — Om angivet försöker systemet sampla deterministiskt, så att upprepade förfrågningar med samma seed och parametrar bör ge samma resultat. Determinism garanteras inte. Måste vara ett heltal mellan 0 och 2147483647.
- `use_multi_channel` (boolean, optional) — Om ljudfilen innehåller flera kanaler där varje kanal innehåller en enda talare. När funktionen är aktiverad transkriberas varje kanal separat. Som standard returneras en separat transkription per kanal; ange multichannel_output_style='combined' för att i stället få en enda transkription där alla kanaler har slagits ihop och sorterats efter tid. Varje ord i svaret innehåller fältet 'channel_index', som anger i vilken kanal det sades. Högst 5 kanaler stöds. Varje kanal debiteras separat för hela ljudlängden, så kostnaden ökar linjärt med antalet kanaler.
- `multichannel_output_style` (enum, optional) — Styr svarsformatet när use_multi_channel är aktiverat. 'separate' (standard) returnerar en transkription per kanal under 'transcripts'. 'combined' sammanfogar alla kanaler till en enda transkription där orden sorteras efter starttid och vart och ett har ett 'channel_index' – samma format som svaret för en kanal. 'combined' kräver tidsstämplar (timestamps_granularity får inte vara 'none') och stöder inte entitetsidentifiering eller maskering.
- `webhook_metadata` (V1SpeechToTextPostRequestBodyContentMultipartFormDataSchemaWebhookMetadata, optional) — Valfria metadata att inkludera i webhook-svaret. Detta ska vara en JSON-sträng som representerar ett objekt med högst 2 nivåers djup och en maximal storlek på 16 KB. Användbart för att spåra interna ID:n, jobbreferenser eller annan kontextuell information.
- `entity_detection` (V1SpeechToTextPostRequestBodyContentMultipartFormDataSchemaEntityDetection, optional) — Identifiera entiteter i transkriptionen. Kan vara 'all' för att identifiera alla entiteter, en enskild entitetstyp eller kategoristräng eller en lista med entitetstyper/kategorier. Kategorierna omfattar 'pii', 'phi', 'pci', 'other', 'offensive_language'. När funktionen är aktiverad returneras identifierade entiteter i fältet 'entities' med text, typ och teckenpositioner.
- `no_verbatim` (boolean, optional) — Om värdet är true innehåller transkriptionen inga utfyllnadsord, felstarter eller icke-talljud. Stöds endast med modellen scribe_v2.
- `use_speaker_library` (boolean, optional) — Om talarbiblioteket ska användas för att identifiera kända talare under diariseringsprocessen. När detta är aktiverat och diarize är true matchas identifierade talare mot registrerade talare i arbetsytans talarbibliotek.
- `detect_speaker_roles` (boolean, optional) — Om talarroller ska identifieras (agent respektive kund). Kräver diarize=true. Kan inte användas med use_multi_channel=true. När funktionen är aktiverad blir speaker_id-värdena 'agent' och 'customer' i stället för 'speaker_0', 'speaker_1' osv. Användning medför ett ytterligare påslag på 10 % av grundkostnaden för transkribering.
- `entity_redaction` (V1SpeechToTextPostRequestBodyContentMultipartFormDataSchemaEntityRedaction, optional) — Maskera entiteter i transkriptionstexten. Accepterar samma format som entity_detection: 'all', en kategori ('pii', 'phi') eller specifika entitetstyper. Måste vara en delmängd av entity_detection. När maskering är aktiverad returneras inte fältet entities.
- `entity_redaction_mode` (string, optional) — Hur maskerade entiteter ska formateras. 'redacted' ersätter med \{REDACTED}, 'entity\_type' ersätter med \{ENTITY\_TYPE} och 'enumerated\_entity\_type' ersätter med \{ENTITY\_TYPE\_N}, där N numrerar varje förekomst. Används endast när entity\_redaction har angetts.
- `keyterms` (list of string, optional) — En lista med nyckeltermer som styr transkriberingen mot dessa. Nyckeltermer är ord eller fraser som du vill att modellen ska känna igen mer exakt. Antalet nyckeltermer får inte överstiga 1 000. Varje nyckelterm måste vara kortare än 50 tecken. Nyckeltermer får innehålla högst 5 ord (efter normalisering). Till exempel \["hello", "world", "technical term"]. Följande tecken stöds inte: `<`, `>`, `{`, `}`, `[`, `]`, `\`. Användning av den här parametern medför en extra avgift på 20 % av baskostnaden för transkribering. När fler än 100 nyckeltermer anges tillämpas en lägsta fakturerbar längd på 20 sekunder per begäran.

## Response

### 200

Synkront transkriptionsresultat

- `speech_to_text_convert_Response_200`
  - SpeechToTextChunkResponseModel: SpeechToTextChunkResponseModel
  - MultichannelSpeechToTextResponseModel: MultichannelSpeechToTextResponseModel
  - SpeechToTextWebhookResponseModel: SpeechToTextWebhookResponseModel

### 202

Asynkron begäran accepterad

## Errors

### 422 Unprocessable Entity Error

Valideringsfel

- `detail` (list of ValidationError, optional)

## Types

### SpeechToTextChunkResponseModel

Detaljer om transkriptionen på chunknivå med tidsinformation.

- `language_code` (string, required) — Den identifierade språkkoden (t.ex. 'eng' för engelska).
- `language_probability` (double, required) — Konfidenspoängen för språkidentifieringen (0 till 1).
- `text` (string, required) — Transkriberingens råtext.
- `words` (list of SpeechToTextWordResponseModel, required) — Lista över ord med tidsinformation.
- `channel_index` (integer, optional, nullable) — Kanalindexet som denna transkription tillhör (för flerkanaligt ljud).
- `additional_formats` (list of AdditionalFormatResponseModel, optional, nullable) — Begärda ytterligare format för transkriberingen.
- `transcription_id` (string, optional, nullable) — Transkriberings-ID:t för svaret.
- `entities` (list of DetectedEntity, optional, nullable) — Lista över identifierade entiteter med deras text, typ och teckenpositioner i transkriptet.
- `audio_duration_secs` (double, optional, nullable) — Längden i sekunder för ljudet som transkriberades.
- `edited_transcript` (SpeechToTextChunkResponseModelEditedTranscript, optional, nullable) — Resultatet av den valfria transkriptredigeringen: den redigerade texten eller ett fel om den inte kunde skapas. Saknas om ingen redigering begärdes. Vid lyckat resultat innehåller både `text` och `edited_text` det redigerade transkriptet. Jämför dem med `text` på högsta nivån för att se vad som ändrades.

### MultichannelSpeechToTextResponseModel

Svarsmodell för flerkanalig tal-till-text-transkribering.

- `transcripts` (list of SpeechToTextChunkResponseModel, required) — Lista över transkriptioner, en för varje ljudkanal. Varje transkription innehåller texten och information på ordnivå för sin kanal.
- `transcription_id` (string, optional, nullable) — Transkriberings-ID:t för svaret.
- `audio_duration_secs` (double, optional, nullable) — Längden i sekunder för ljudet som transkriberades över alla kanaler.

### SpeechToTextWebhookResponseModel

- `message` (string, required) — Meddelandet i webhook-svaret.
- `request_id` (string, required) — Begärande-ID:t för webhook-svaret.
- `transcription_id` (string, optional, nullable) — Transkriberings-ID:t för webhooksvaret.

### ValidationError

- `loc` (list of ValidationErrorLocItems, required)
- `msg` (string, required)
- `type` (string, required)

### SpeechToTextWordResponseModel

Information på ordnivå i transkriberingen med tidsinformation.

- `text` (string, required) — Ordet eller ljudet som transkriberades.
- `type` (enum, required) — Typen av ord eller ljud. 'audio_event' används för ljud som inte är ord, till exempel skratt eller fotsteg.
  - Allowed values: `word`, `spacing`, `audio_event`
- `logprob` (double, required) — Logaritmen av sannolikheten med vilken detta ord förutsades. Logprobs ligger i intervallet [-infinity, 0]; högre logprobs innebär att modellen har större tilltro till sina förutsägelser.
- `start` (double, optional, nullable) — Starttiden för ordet eller ljudet i sekunder.
- `end` (double, optional, nullable) — Ordets eller ljudets sluttid i sekunder.
- `speaker_id` (string, optional, nullable) — Unik identifierare för talaren av detta ord.
- `characters` (list of SpeechToTextCharacterResponseModel, optional, nullable) — Tecknen som utgör ordet och deras tidsinformation.
- `channel_index` (integer, optional, nullable) — Kanalen som detta ord sades på (för flerkanaligt ljud). Null för enkanaliga transkriptioner.

### AdditionalFormatResponseModel

- `requested_format` (string, required) — Det begärda formatet.
- `file_extension` (string, required) — Filtillägget för det extra formatet.
- `content_type` (string, required) — Innehållstypen för det extra formatet.
- `is_base64_encoded` (boolean, required) — Om innehållet är base64-kodat.
- `content` (string, required) — Innehållet i det extra formatet.

### DetectedEntity

An entity detected within transcribed text.

- `text` (string, required) — The text that was identified as an entity.
- `entity_type` (string, required) — The type of entity detected (e.g., 'credit_card', 'email_address', 'person_name').
- `start_char` (integer, required) — Start character position in the transcript text.
- `end_char` (integer, required) — End character position in the transcript text.

### SpeechToTextChunkResponseModelEditedTranscript

Resultatet av den valfria transkriptredigeringen: den redigerade texten eller ett fel om den inte kunde skapas. Saknas om ingen redigering begärdes. Vid lyckat resultat innehåller både `text` och `edited_text` det redigerade transkriptet. Jämför dem med `text` på högsta nivån för att se vad som ändrades.

- `kind`: `error` (TranscriptEditError)
  - `error_type` ("edit_failed", required) — edit_failed: redigeringen kunde inte genomföras.
  - `message` (string, required) — En kort, användarvänlig förklaring av felet.
- `kind`: `transcript` (EditedTranscript)
  - `edited_text` (string, required) — The edited transcript text. If no edits were made it will be identical to the `text` field.
  - `text` (string, required) — The committed transcript text the edit instruction was applied to.
  - `message_type` (string, optional, default: edited_transcript)

### ValidationErrorLocItems

- string
- integer

### SpeechToTextCharacterResponseModel

- `text` (string, required) — Tecknet som transkriberades.
- `start` (double, optional, nullable) — Starttiden för tecknet i sekunder.
- `end` (double, optional, nullable) — Tecknets sluttid i sekunder.

## Examples

### Example_0

**Request**

```json
{
  "file": "<file: <file1>>",
  "model_id": "scribe_v2"
}
```

**Response**

```json
{
  "language_code": "en",
  "language_probability": 0.98,
  "text": "Hello world!",
  "words": [
    {
      "end": 0.5,
      "logprob": -0.124,
      "speaker_id": "speaker_1",
      "start": 0,
      "text": "Hello",
      "type": "word"
    }
  ]
}
```

**SDK Code**

```python Example_0
import requests

url = "https://api.elevenlabs.io/v1/speech-to-text"

querystring = {"enable_logging":"true","token":"token"}

files = { "file": "open('<file1>', 'rb')" }
payload = {
    "additional_formats": ,
    "cloud_storage_url": ,
    "detect_speaker_roles": ,
    "diarization_threshold": ,
    "diarize": ,
    "entity_detection": ,
    "entity_redaction": ,
    "entity_redaction_mode": ,
    "file_format": ,
    "keyterms": ,
    "language_code": ,
    "model_id": "scribe_v2",
    "multichannel_output_style": ,
    "no_verbatim": ,
    "num_speakers": ,
    "seed": ,
    "source_url": ,
    "tag_audio_events": ,
    "temperature": ,
    "timestamps_granularity": ,
    "transcript_edit": ,
    "use_multi_channel": ,
    "use_speaker_library": ,
    "webhook": ,
    "webhook_id": ,
    "webhook_metadata": 
}
headers = {"xi-api-key": "xi-api-key"}

response = requests.post(url, data=payload, files=files, headers=headers, params=querystring)

print(response.json())
```

```javascript Example_0
const url = 'https://api.elevenlabs.io/v1/speech-to-text?enable_logging=true&token=token';
const form = new FormData();
form.append('additional_formats', '');
form.append('cloud_storage_url', '');
form.append('detect_speaker_roles', '');
form.append('diarization_threshold', '');
form.append('diarize', '');
form.append('entity_detection', '');
form.append('entity_redaction', '');
form.append('entity_redaction_mode', '');
form.append('file', '<file1>');
form.append('file_format', '');
form.append('keyterms', '');
form.append('language_code', '');
form.append('model_id', 'scribe_v2');
form.append('multichannel_output_style', '');
form.append('no_verbatim', '');
form.append('num_speakers', '');
form.append('seed', '');
form.append('source_url', '');
form.append('tag_audio_events', '');
form.append('temperature', '');
form.append('timestamps_granularity', '');
form.append('transcript_edit', '');
form.append('use_multi_channel', '');
form.append('use_speaker_library', '');
form.append('webhook', '');
form.append('webhook_id', '');
form.append('webhook_metadata', '');

const options = {method: 'POST', headers: {'xi-api-key': 'xi-api-key'}};

options.body = form;

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go Example_0
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.elevenlabs.io/v1/speech-to-text?enable_logging=true&token=token"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"additional_formats\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"cloud_storage_url\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"detect_speaker_roles\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarization_threshold\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_detection\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_redaction\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_redaction_mode\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"<file1>\"\r\nContent-Type: application/octet-stream\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_format\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"keyterms\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language_code\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"multichannel_output_style\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"no_verbatim\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"num_speakers\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"seed\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_url\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"tag_audio_events\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps_granularity\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"transcript_edit\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_multi_channel\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_speaker_library\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_id\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_metadata\"\r\n\r\n\r\n-----011000010111000001101001--\r\n")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("xi-api-key", "xi-api-key")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby Example_0
require 'uri'
require 'net/http'

url = URI("https://api.elevenlabs.io/v1/speech-to-text?enable_logging=true&token=token")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["xi-api-key"] = 'xi-api-key'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"additional_formats\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"cloud_storage_url\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"detect_speaker_roles\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarization_threshold\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_detection\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_redaction\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_redaction_mode\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"<file1>\"\r\nContent-Type: application/octet-stream\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_format\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"keyterms\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language_code\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"multichannel_output_style\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"no_verbatim\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"num_speakers\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"seed\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_url\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"tag_audio_events\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps_granularity\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"transcript_edit\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_multi_channel\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_speaker_library\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_id\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_metadata\"\r\n\r\n\r\n-----011000010111000001101001--\r\n"

response = http.request(request)
puts response.read_body
```

```java Example_0
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.elevenlabs.io/v1/speech-to-text?enable_logging=true&token=token")
  .header("xi-api-key", "xi-api-key")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"additional_formats\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"cloud_storage_url\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"detect_speaker_roles\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarization_threshold\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_detection\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_redaction\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_redaction_mode\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"<file1>\"\r\nContent-Type: application/octet-stream\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_format\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"keyterms\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language_code\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"multichannel_output_style\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"no_verbatim\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"num_speakers\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"seed\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_url\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"tag_audio_events\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps_granularity\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"transcript_edit\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_multi_channel\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_speaker_library\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_id\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_metadata\"\r\n\r\n\r\n-----011000010111000001101001--\r\n")
  .asString();
```

```php Example_0
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.elevenlabs.io/v1/speech-to-text?enable_logging=true&token=token', [
  'multipart' => [
    [
        'name' => 'file',
        'filename' => '<file1>',
        'contents' => null
    ],
    [
        'name' => 'model_id',
        'contents' => 'scribe_v2'
    ]
  ]
  'headers' => [
    'xi-api-key' => 'xi-api-key',
  ],
]);

echo $response->getBody();
```

```csharp Example_0
using RestSharp;

var client = new RestClient("https://api.elevenlabs.io/v1/speech-to-text?enable_logging=true&token=token");
var request = new RestRequest(Method.POST);
request.AddHeader("xi-api-key", "xi-api-key");
request.AddParameter("undefined", "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"additional_formats\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"cloud_storage_url\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"detect_speaker_roles\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarization_threshold\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_detection\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_redaction\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_redaction_mode\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"<file1>\"\r\nContent-Type: application/octet-stream\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_format\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"keyterms\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language_code\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"multichannel_output_style\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"no_verbatim\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"num_speakers\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"seed\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_url\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"tag_audio_events\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps_granularity\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"transcript_edit\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_multi_channel\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_speaker_library\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_id\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_metadata\"\r\n\r\n\r\n-----011000010111000001101001--\r\n", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift Example_0
import Foundation

let headers = ["xi-api-key": "xi-api-key"]
let parameters = [
  [
    "name": "additional_formats",
    "value": 
  ],
  [
    "name": "cloud_storage_url",
    "value": 
  ],
  [
    "name": "detect_speaker_roles",
    "value": 
  ],
  [
    "name": "diarization_threshold",
    "value": 
  ],
  [
    "name": "diarize",
    "value": 
  ],
  [
    "name": "entity_detection",
    "value": 
  ],
  [
    "name": "entity_redaction",
    "value": 
  ],
  [
    "name": "entity_redaction_mode",
    "value": 
  ],
  [
    "name": "file",
    "fileName": "<file1>"
  ],
  [
    "name": "file_format",
    "value": 
  ],
  [
    "name": "keyterms",
    "value": 
  ],
  [
    "name": "language_code",
    "value": 
  ],
  [
    "name": "model_id",
    "value": "scribe_v2"
  ],
  [
    "name": "multichannel_output_style",
    "value": 
  ],
  [
    "name": "no_verbatim",
    "value": 
  ],
  [
    "name": "num_speakers",
    "value": 
  ],
  [
    "name": "seed",
    "value": 
  ],
  [
    "name": "source_url",
    "value": 
  ],
  [
    "name": "tag_audio_events",
    "value": 
  ],
  [
    "name": "temperature",
    "value": 
  ],
  [
    "name": "timestamps_granularity",
    "value": 
  ],
  [
    "name": "transcript_edit",
    "value": 
  ],
  [
    "name": "use_multi_channel",
    "value": 
  ],
  [
    "name": "use_speaker_library",
    "value": 
  ],
  [
    "name": "webhook",
    "value": 
  ],
  [
    "name": "webhook_id",
    "value": 
  ],
  [
    "name": "webhook_metadata",
    "value": 
  ]
]

let boundary = "---011000010111000001101001"

var body = ""
var error: NSError? = nil
for param in parameters {
  let paramName = param["name"]!
  body += "--\(boundary)\r\n"
  body += "Content-Disposition:form-data; name=\"\(paramName)\""
  if let filename = param["fileName"] {
    let contentType = param["content-type"]!
    let fileContent = String(contentsOfFile: filename, encoding: String.Encoding.utf8)
    if (error != nil) {
      print(error as Any)
    }
    body += "; filename=\"\(filename)\"\r\n"
    body += "Content-Type: \(contentType)\r\n\r\n"
    body += fileContent
  } else if let paramValue = param["value"] {
    body += "\r\n\r\n\(paramValue)"
  }
}

let request = NSMutableURLRequest(url: NSURL(string: "https://api.elevenlabs.io/v1/speech-to-text?enable_logging=true&token=token")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```

### Example_1

**Request**

```json
{
  "file": "<file: <file1>>",
  "model_id": "scribe_v2"
}
```

**Response**

```json
{
  "transcripts": [
    {
      "language_code": "en",
      "language_probability": 0.98,
      "text": "Hello from channel one.",
      "words": [
        {
          "channel_index": 0,
          "end": 0.5,
          "logprob": -0.124,
          "speaker_id": "speaker_0",
          "start": 0,
          "text": "Hello",
          "type": "word"
        }
      ]
    },
    {
      "language_code": "en",
      "language_probability": 0.97,
      "text": "Greetings from channel two.",
      "words": [
        {
          "channel_index": 1,
          "end": 0.7,
          "logprob": -0.156,
          "speaker_id": "speaker_1",
          "start": 0.1,
          "text": "Greetings",
          "type": "word"
        }
      ]
    }
  ]
}
```

**SDK Code**

```python Example_1
import requests

url = "https://api.elevenlabs.io/v1/speech-to-text"

querystring = {"enable_logging":"true","token":"token"}

files = { "file": "open('<file1>', 'rb')" }
payload = {
    "additional_formats": ,
    "cloud_storage_url": ,
    "detect_speaker_roles": ,
    "diarization_threshold": ,
    "diarize": ,
    "entity_detection": ,
    "entity_redaction": ,
    "entity_redaction_mode": ,
    "file_format": ,
    "keyterms": ,
    "language_code": ,
    "model_id": "scribe_v2",
    "multichannel_output_style": ,
    "no_verbatim": ,
    "num_speakers": ,
    "seed": ,
    "source_url": ,
    "tag_audio_events": ,
    "temperature": ,
    "timestamps_granularity": ,
    "transcript_edit": ,
    "use_multi_channel": ,
    "use_speaker_library": ,
    "webhook": ,
    "webhook_id": ,
    "webhook_metadata": 
}
headers = {"xi-api-key": "xi-api-key"}

response = requests.post(url, data=payload, files=files, headers=headers, params=querystring)

print(response.json())
```

```javascript Example_1
const url = 'https://api.elevenlabs.io/v1/speech-to-text?enable_logging=true&token=token';
const form = new FormData();
form.append('additional_formats', '');
form.append('cloud_storage_url', '');
form.append('detect_speaker_roles', '');
form.append('diarization_threshold', '');
form.append('diarize', '');
form.append('entity_detection', '');
form.append('entity_redaction', '');
form.append('entity_redaction_mode', '');
form.append('file', '<file1>');
form.append('file_format', '');
form.append('keyterms', '');
form.append('language_code', '');
form.append('model_id', 'scribe_v2');
form.append('multichannel_output_style', '');
form.append('no_verbatim', '');
form.append('num_speakers', '');
form.append('seed', '');
form.append('source_url', '');
form.append('tag_audio_events', '');
form.append('temperature', '');
form.append('timestamps_granularity', '');
form.append('transcript_edit', '');
form.append('use_multi_channel', '');
form.append('use_speaker_library', '');
form.append('webhook', '');
form.append('webhook_id', '');
form.append('webhook_metadata', '');

const options = {method: 'POST', headers: {'xi-api-key': 'xi-api-key'}};

options.body = form;

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go Example_1
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.elevenlabs.io/v1/speech-to-text?enable_logging=true&token=token"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"additional_formats\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"cloud_storage_url\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"detect_speaker_roles\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarization_threshold\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_detection\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_redaction\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_redaction_mode\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"<file1>\"\r\nContent-Type: application/octet-stream\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_format\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"keyterms\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language_code\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"multichannel_output_style\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"no_verbatim\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"num_speakers\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"seed\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_url\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"tag_audio_events\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps_granularity\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"transcript_edit\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_multi_channel\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_speaker_library\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_id\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_metadata\"\r\n\r\n\r\n-----011000010111000001101001--\r\n")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("xi-api-key", "xi-api-key")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby Example_1
require 'uri'
require 'net/http'

url = URI("https://api.elevenlabs.io/v1/speech-to-text?enable_logging=true&token=token")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["xi-api-key"] = 'xi-api-key'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"additional_formats\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"cloud_storage_url\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"detect_speaker_roles\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarization_threshold\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_detection\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_redaction\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_redaction_mode\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"<file1>\"\r\nContent-Type: application/octet-stream\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_format\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"keyterms\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language_code\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"multichannel_output_style\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"no_verbatim\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"num_speakers\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"seed\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_url\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"tag_audio_events\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps_granularity\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"transcript_edit\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_multi_channel\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_speaker_library\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_id\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_metadata\"\r\n\r\n\r\n-----011000010111000001101001--\r\n"

response = http.request(request)
puts response.read_body
```

```java Example_1
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.elevenlabs.io/v1/speech-to-text?enable_logging=true&token=token")
  .header("xi-api-key", "xi-api-key")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"additional_formats\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"cloud_storage_url\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"detect_speaker_roles\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarization_threshold\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_detection\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_redaction\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_redaction_mode\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"<file1>\"\r\nContent-Type: application/octet-stream\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_format\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"keyterms\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language_code\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"multichannel_output_style\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"no_verbatim\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"num_speakers\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"seed\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_url\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"tag_audio_events\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps_granularity\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"transcript_edit\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_multi_channel\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_speaker_library\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_id\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_metadata\"\r\n\r\n\r\n-----011000010111000001101001--\r\n")
  .asString();
```

```php Example_1
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.elevenlabs.io/v1/speech-to-text?enable_logging=true&token=token', [
  'multipart' => [
    [
        'name' => 'file',
        'filename' => '<file1>',
        'contents' => null
    ],
    [
        'name' => 'model_id',
        'contents' => 'scribe_v2'
    ]
  ]
  'headers' => [
    'xi-api-key' => 'xi-api-key',
  ],
]);

echo $response->getBody();
```

```csharp Example_1
using RestSharp;

var client = new RestClient("https://api.elevenlabs.io/v1/speech-to-text?enable_logging=true&token=token");
var request = new RestRequest(Method.POST);
request.AddHeader("xi-api-key", "xi-api-key");
request.AddParameter("undefined", "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"additional_formats\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"cloud_storage_url\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"detect_speaker_roles\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarization_threshold\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_detection\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_redaction\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"entity_redaction_mode\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"<file1>\"\r\nContent-Type: application/octet-stream\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_format\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"keyterms\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language_code\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"multichannel_output_style\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"no_verbatim\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"num_speakers\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"seed\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"source_url\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"tag_audio_events\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps_granularity\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"transcript_edit\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_multi_channel\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"use_speaker_library\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_id\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_metadata\"\r\n\r\n\r\n-----011000010111000001101001--\r\n", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift Example_1
import Foundation

let headers = ["xi-api-key": "xi-api-key"]
let parameters = [
  [
    "name": "additional_formats",
    "value": 
  ],
  [
    "name": "cloud_storage_url",
    "value": 
  ],
  [
    "name": "detect_speaker_roles",
    "value": 
  ],
  [
    "name": "diarization_threshold",
    "value": 
  ],
  [
    "name": "diarize",
    "value": 
  ],
  [
    "name": "entity_detection",
    "value": 
  ],
  [
    "name": "entity_redaction",
    "value": 
  ],
  [
    "name": "entity_redaction_mode",
    "value": 
  ],
  [
    "name": "file",
    "fileName": "<file1>"
  ],
  [
    "name": "file_format",
    "value": 
  ],
  [
    "name": "keyterms",
    "value": 
  ],
  [
    "name": "language_code",
    "value": 
  ],
  [
    "name": "model_id",
    "value": "scribe_v2"
  ],
  [
    "name": "multichannel_output_style",
    "value": 
  ],
  [
    "name": "no_verbatim",
    "value": 
  ],
  [
    "name": "num_speakers",
    "value": 
  ],
  [
    "name": "seed",
    "value": 
  ],
  [
    "name": "source_url",
    "value": 
  ],
  [
    "name": "tag_audio_events",
    "value": 
  ],
  [
    "name": "temperature",
    "value": 
  ],
  [
    "name": "timestamps_granularity",
    "value": 
  ],
  [
    "name": "transcript_edit",
    "value": 
  ],
  [
    "name": "use_multi_channel",
    "value": 
  ],
  [
    "name": "use_speaker_library",
    "value": 
  ],
  [
    "name": "webhook",
    "value": 
  ],
  [
    "name": "webhook_id",
    "value": 
  ],
  [
    "name": "webhook_metadata",
    "value": 
  ]
]

let boundary = "---011000010111000001101001"

var body = ""
var error: NSError? = nil
for param in parameters {
  let paramName = param["name"]!
  body += "--\(boundary)\r\n"
  body += "Content-Disposition:form-data; name=\"\(paramName)\""
  if let filename = param["fileName"] {
    let contentType = param["content-type"]!
    let fileContent = String(contentsOfFile: filename, encoding: String.Encoding.utf8)
    if (error != nil) {
      print(error as Any)
    }
    body += "; filename=\"\(filename)\"\r\n"
    body += "Content-Type: \(contentType)\r\n\r\n"
    body += fileContent
  } else if let paramValue = param["value"] {
    body += "\r\n\r\n\(paramValue)"
  }
}

let request = NSMutableURLRequest(url: NSURL(string: "https://api.elevenlabs.io/v1/speech-to-text?enable_logging=true&token=token")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```