curl -X POST 'https://api.elevenlabs.io/v1/speech-engine' \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "name": "Speech Engine",
  "speech_engine": {
    "ws_url": "string",
    "request_headers": {}
  },
  "asr": {
    "keywords": [
      "hello",
      "world"
    ],
    "provider": "scribe_realtime",
    "quality": "high",
    "user_input_audio_format": "pcm_16000"
  },
  "tts": {
    "agent_output_audio_format": "pcm_16000",
    "model_id": "eleven_turbo_v2",
    "optimize_streaming_latency": 3,
    "pronunciation_dictionary_locators": [],
    "similarity_boost": 0.8,
    "speed": 1,
    "stability": 0.5,
    "voice_id": "cjVigY5qzO86Huf0OWal"
  },
  "turn": {
    "interruption_ignore_term_languages": [],
    "interruption_ignore_terms": [],
    "merge_with_default_ignore_terms": false,
    "mode": "turn",
    "retranscribe_on_turn_timeout": false,
    "silence_end_call_timeout": -1,
    "speculative_turn": false,
    "spelling_patience": "auto",
    "transcribe_on_disabled_interruptions": false,
    "turn_eagerness": "normal",
    "turn_timeout": 7
  },
  "vad": {
    "background_voice_detection": false
  },
  "conversation": {
    "client_events": [
      "audio",
      "interruption"
    ],
    "max_duration_seconds": 600
  },
  "privacy": {
    "apply_to_existing_conversations": false,
    "delete_audio": false,
    "delete_transcript_and_pii": false,
    "record_voice": true,
    "retention_days": -1,
    "zero_retention_mode": false
  },
  "call_limits": {
    "agent_concurrency_limit": -1,
    "bursting_enabled": true,
    "daily_limit": 100000
  },
  "language": "en",
  "tags": [
    "string"
  ],
  "overrides": {
    "first_message": false
  }
}'

# POST /v1/speech-engine (ElevenLabs API)
Base URL: https://api.elevenlabs.io
Auth: xi-api-key: <ELEVENLABS_API_KEY>
Last verified: 2026-09-03

> Create Speech Engine

## Critical Gotchas
* Authentication uses the non-standard `xi-api-key` header, not `Authorization: Bearer`. Sending a Bearer token returns HTTP 401.
* Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (`--output speech.mp3`) rather than parsing it.

## cURL
curl -X POST 'https://api.elevenlabs.io/v1/speech-engine' \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"name":"Speech Engine","speech_engine":{"ws_url":"string","request_headers":{}}}'

## Parameters
| Name | In | Type | Required | Description |
| :--- | :--- | :--- | :--- | :--- |
| speech_engine | body | object | Yes | Request body field speech_engine. |
| name | body | string | No | Name of the speech engine |
| asr | body | object | No | Request body field asr. |
| tts | body | object | No | Request body field tts. |

## Response (200 OK)
{"asr":{"keywords":[],"provider":"elevenlabs"},"call_limits":{"agent_concurrency_limit":-1,"bursting_enabled":true}}

---
Need an API key? Get one at https://elevenlabs.io/app/sign-up

POST

/v1/speech-engine

ElevenLabs API

Create Speech Engine

Base URL: https://api.elevenlabs.io
Auth: xi-api-key: <ELEVENLABS_API_KEY>
Last verified: 2026-09-03 · upstream hash matched

Actions

Agents: curl -H "Accept: text/markdown" this URL
→ 224 tokens · Vary: Accept

Critical gotchas

Authentication uses the non-standard xi-api-key header, not Authorization: Bearer. Sending a Bearer token returns HTTP 401.

Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (--output speech.mp3) rather than parsing it.

cURL

curl -X POST 'https://api.elevenlabs.io/v1/speech-engine' \  -H "xi-api-key: $ELEVENLABS_API_KEY" \  -H 'Content-Type: application/json' \  -d '{  "name": "Speech Engine",  "speech_engine": {    "ws_url": "string",    "request_headers": {}  },  "asr": {    "keywords": [      "hello",      "world"    ],    "provider": "scribe_realtime",    "quality": "high",    "user_input_audio_format": "pcm_16000"  },  "tts": {    "agent_output_audio_format": "pcm_16000",    "model_id": "eleven_turbo_v2",    "optimize_streaming_latency": 3,    "pronunciation_dictionary_locators": [],    "similarity_boost": 0.8,    "speed": 1,    "stability": 0.5,    "voice_id": "cjVigY5qzO86Huf0OWal"  },  "turn": {    "interruption_ignore_term_languages": [],    "interruption_ignore_terms": [],    "merge_with_default_ignore_terms": false,    "mode": "turn",    "retranscribe_on_turn_timeout": false,    "silence_end_call_timeout": -1,    "speculative_turn": false,    "spelling_patience": "auto",    "transcribe_on_disabled_interruptions": false,    "turn_eagerness": "normal",    "turn_timeout": 7  },  "vad": {    "background_voice_detection": false  },  "conversation": {    "client_events": [      "audio",      "interruption"    ],    "max_duration_seconds": 600  },  "privacy": {    "apply_to_existing_conversations": false,    "delete_audio": false,    "delete_transcript_and_pii": false,    "record_voice": true,    "retention_days": -1,    "zero_retention_mode": false  },  "call_limits": {    "agent_concurrency_limit": -1,    "bursting_enabled": true,    "daily_limit": 100000  },  "language": "en",  "tags": [    "string"  ],  "overrides": {    "first_message": false  }}'

Get a free ElevenLabs API key → sponsored

Parameters

Name	In	Type	Required	Description
name	body	string	No	Name of the speech engine
speech_engine	body	object	Yes	Request body field speech_engine.
asr	body	object	No	Request body field asr.
tts	body	object	No	Request body field tts.
turn	body	object	No	Request body field turn.
vad	body	object	No	Request body field vad.
conversation	body	object	No	Request body field conversation.
privacy	body	object	No	Request body field privacy.
call_limits	body	object	No	Request body field call_limits.
language	body	string	No	Language for the speech engine
tags	body	string[]	No	Tags for categorization
overrides	body	object	No	Request body field overrides.

Response 200 OK

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