For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Connect
BlogHelp CenterAPI PricingSign up
OverviewElevenCreativeElevenAgentsElevenAPIAPI referenceChangelog
OverviewElevenCreativeElevenAgentsElevenAPIAPI referenceChangelog
  • API reference
    • Introduction
    • Authentication
    • Streaming
  • ElevenAgents
  • ElevenAPI
      • POSTCreate dialogue
      • STREAMStream dialogue
      • POSTCreate dialogue with timestamps
      • STREAMStream dialogue with timestamps
  • ElevenCreative
  • Core Resources
  • Workspace
  • Legacy
LogoLogo
Login
Login
Connect
BlogHelp CenterAPI PricingSign up
ElevenAPIText to Dialogue

Create dialogue with timestamps

POST
/v1/text-to-dialogue/with-timestamps
POST
/v1/text-to-dialogue/with-timestamps
$curl -X POST https://api.elevenlabs.io/v1/text-to-dialogue/with-timestamps \
>     -H "Content-Type: application/json" \
>     -d '{
>  "inputs": [
>    {
>      "text": "Hello, how are you?",
>      "voice_id": "bYTqZQo3Jz7LQtmGTgwi"
>    },
>    {
>      "text": "I'\''m doing well, thank you!",
>      "voice_id": "6lCwbsX1yVjD49QmpkTR"
>    }
>  ]
>}'
1{
2  "audio_base64": "base64_encoded_audio_string",
3  "voice_segments": [
4    {
5      "voice_id": "21m00Tcm4TlvDq8ikWAM",
6      "start_time_seconds": 0,
7      "end_time_seconds": 0.5,
8      "character_start_index": 0,
9      "character_end_index": 5,
10      "dialogue_input_index": 0
11    },
12    {
13      "voice_id": "VEDscrYI8uIMttlO2Ztu",
14      "start_time_seconds": 0.5,
15      "end_time_seconds": 0.7,
16      "character_start_index": 5,
17      "character_end_index": 7,
18      "dialogue_input_index": 1
19    }
20  ],
21  "alignment": {
22    "characters": [
23      "H",
24      "e",
25      "l",
26      "l",
27      "o",
28      "H",
29      "i"
30    ],
31    "character_start_times_seconds": [
32      0,
33      0.1,
34      0.2,
35      0.3,
36      0.4,
37      0.5,
38      0.6
39    ],
40    "character_end_times_seconds": [
41      0.1,
42      0.2,
43      0.3,
44      0.4,
45      0.5,
46      0.6,
47      0.7
48    ]
49  },
50  "normalized_alignment": {
51    "characters": [
52      "H",
53      "e",
54      "l",
55      "l",
56      "o",
57      "H",
58      "i"
59    ],
60    "character_start_times_seconds": [
61      0,
62      0.1,
63      0.2,
64      0.3,
65      0.4,
66      0.5,
67      0.6
68    ],
69    "character_end_times_seconds": [
70      0.1,
71      0.2,
72      0.3,
73      0.4,
74      0.5,
75      0.6,
76      0.7
77    ]
78  }
79}

Generate dialogue from text with precise character-level timing information for audio-text synchronization.

Was this page helpful?
Previous

Stream dialogue with timestamps

Next
Built with

Headers

xi-api-keystringOptional

Query parameters

output_formatenumOptionalDefaults to mp3_44100_128
Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM and WAV formats with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.

Request

This endpoint expects an object.
inputslist of objectsRequired

A list of dialogue inputs, each containing text and a voice ID which will be converted into speech. The maximum number of unique voice IDs is 10. For reliable generation, keep the total character count across all inputs[].text values at or below 2,000 characters per request. Longer requests can terminate early in streaming responses or return a validation error.

model_idstringOptionalDefaults to eleven_v3

Identifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for text to speech, you can check this using the can_do_text_to_speech property.

language_codestring or nullOptional

Language code (ISO 639-1) used to enforce a language for the model and text normalization. If the model does not support provided language code, an error will be returned.

settingsobject or nullOptional
Settings controlling the dialogue generation.
pronunciation_dictionary_locatorslist of objects or nullOptional

A list of pronunciation dictionary locators (id, version_id) to be applied to the text. They will be applied in order. You may have up to 3 locators per request

seedinteger or nullOptional
If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be integer between 0 and 4294967295.
apply_text_normalizationenumOptionalDefaults to auto

This parameter controls text normalization with three modes: ‘auto’, ‘on’, and ‘off’. When set to ‘auto’, the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With ‘on’, text normalization will always be applied, while with ‘off’, it will be skipped.

Allowed values:

Response

Successful Response
audio_base64string
Base64 encoded audio data
voice_segmentslist of objects
Voice segments for the audio
alignmentobject or null
Timestamp information for each character in the original text
normalized_alignmentobject or null
Timestamp information for each character in the normalized text

Errors

422
Unprocessable Entity Error

Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM and WAV formats with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.