Create speech engine | ElevenLabs Documentation

curl -X POST https://api.elevenlabs.io/v1/speech-engine \
     -H "Content-Type: application/json" \
     -d '{
  "speech_engine": {
    "ws_url": "string"
  }
}'

{
  "speech_engine_id": "seng_3701k3ttaq12ewp8b7qv5rfyszkz",
  "name": "My Speech Engine",
  "speech_engine": {
    "ws_url": "wss://example.com/transcript",
    "request_headers": {}
  },
  "asr": {
    "quality": "high",
    "provider": "elevenlabs",
    "user_input_audio_format": "pcm_16000",
    "keywords": []
  },
  "tts": {
    "model_id": "eleven_flash_v2",
    "voice_id": "cjVigY5qzO86Huf0OWal",
    "agent_output_audio_format": "pcm_16000",
    "optimize_streaming_latency": 3,
    "stability": 0.5,
    "speed": 1,
    "similarity_boost": 0.8
  },
  "turn": {
    "turn_timeout": 7,
    "silence_end_call_timeout": -1,
    "turn_eagerness": "normal",
    "mode": "turn"
  },
  "conversation": {
    "max_duration_seconds": 600,
    "client_events": [
      "audio",
      "interruption",
      "agent_response",
      "user_transcript"
    ]
  },
  "privacy": {
    "record_voice": true,
    "retention_days": -1,
    "delete_transcript_and_pii": false,
    "delete_audio": false,
    "apply_to_existing_conversations": false,
    "zero_retention_mode": false
  },
  "call_limits": {
    "agent_concurrency_limit": -1,
    "daily_limit": 100000,
    "bursting_enabled": true
  },
  "language": "en",
  "tags": [
    "production",
    "v1"
  ],
  "overrides": {
    "first_message": false
  },
  "metadata": {
    "created_at_unix_secs": 1714000000,
    "updated_at_unix_secs": 1714000000,
    "created_from": "api",
    "last_updated_from": "api"
  }
}

Create a new Speech Engine resource

Request

This endpoint expects an object.

speech_engineobjectRequired

Speech engine WebSocket configuration

namestringOptionalDefaults to Speech Engine

Name of the speech engine

asrobjectOptional

ASR configuration

ttsobjectOptional

TTS configuration

turnobjectOptional

Turn detection configuration

conversationobjectOptional

Conversation configuration (client events, etc.)

privacyobjectOptional

Privacy settings (recording, retention, zero retention mode)

call_limitsobjectOptional

Concurrency and daily conversation limits for this speech engine

languagestringOptionalDefaults to en

Language for the speech engine

tagslist of stringsOptional

Tags for categorization

overridesobjectOptional

Override settings the client may set during conversation initiation

Response

Successful Response

speech_engine_idstring

The speech engine resource ID

namestring

Human-readable name for the speech engine

speech_engineobject

WebSocket connection settings for the upstream transcript server

asrobject

Automatic speech recognition configuration

ttsobject

Text-to-speech output configuration

turnobject

Turn detection configuration

conversationobject

Conversation-level settings including client events and duration limits

privacyobject

Privacy settings controlling recording, retention, and PII handling

call_limitsobject

Concurrency and daily conversation limits for this speech engine

languagestring

ISO language code used by the speech engine (e.g. ‘en’)

tagslist of strings

Arbitrary tags for categorization and filtering

overridesobject

Override settings the client may set during conversation initiation

metadataobject

Creation and update timestamps with source information

Errors

422

Unprocessable Entity Error

Headers

Request

Response

Errors