创建语音引擎

POST

/v1/speech-engine

POST

/v1/speech-engine

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",
    "stability": 0.5,
    "speed": 1,
    "similarity_boost": 0.8,
    "optimize_streaming_latency": 3
  },
  "turn": {
    "turn_timeout": 7,
    "silence_end_call_timeout": -1,
    "turn_eagerness": "normal",
    "mode": "turn"
  },
  "vad": {
    "background_voice_detection": false
  },
  "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",
  "cascade_timeout_seconds": 4,
  "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"
  }
}

创建新的 Speech Engine 资源

请求

This endpoint expects an object.

speech_engineobject必需

语音引擎 WebSocket 配置

namestring可选默认为 Speech Engine

语音引擎名称

asrobject可选

ASR configuration

ttsobject可选

TTS 配置。

turnobject可选

轮次检测配置。

vadobject可选

Configuration for voice activity detection

conversationobject可选

对话配置（客户端事件等）

privacyobject可选

隐私设置（录音、保留、零保留模式）

call_limitsobject可选

Concurrency and daily conversation limits for this speech engine

languagestring可选默认为 en

语音引擎语言

cascade_timeout_secondsdouble可选2-15默认为 4

放弃当前尝试并重试前，等待上游语音引擎端点响应的秒数。必须介于 2 至 15 秒。

tagslist of strings可选

分类标签

overridesobject可选

客户端可在发起对话时设置的覆盖选项

响应

成功响应

speech_engine_idstring

语音引擎资源 ID

namestring

语音引擎的人类可读名称

speech_engineobject

上游转写服务器的 WebSocket 连接设置

asrobject

Automatic speech recognition configuration

ttsobject

文本转语音输出配置

turnobject

轮次检测配置。

vadobject

Configuration for voice activity detection

conversationobject

对话级设置，包括客户端事件和时长限制

privacyobject

控制录音、保留和 PII 处理的隐私设置

call_limitsobject

Concurrency and daily conversation limits for this speech engine

languagestring

语音引擎使用的 ISO 语言代码（例如 ‘en’）

cascade_timeout_secondsdouble

放弃当前尝试并重试前，等待上游语音引擎端点响应的秒数。必须介于 2 至 15 秒。

tagslist of strings

用于分类和筛选的任意标签

overridesobject

客户端可在发起对话时设置的覆盖选项

metadataobject

包含来源信息的创建和更新时间戳

access_infoobject or null可选

用户对语音引擎的访问信息

错误

422

Unprocessable Entity Error

请求头

请求

响应

错误