Generic TTS

The generic_http TTS vendor lets you integrate a custom TTS service that implements the OpenAI TTS protocol into the Conversational AI Engine. For a walkthrough of preparing and verifying a compatible TTS service, see Connect your own TTS service.

Sample configuration

Use the following tts configuration when starting a conversational AI agent using the REST API. generic_http requires tts.url, and at least one of tts.headers.Authorization or tts.params.api_key for authentication.

• Authenticate using headers (recommended)

  "tts": {
    "vendor": "generic_http",
    "url": "https://your-tts-service.example.com/v1/audio/speech",
    "headers": {
      "Authorization": "Bearer your_tts_api_key"
    },
    "params": {
      "model": "gpt-4o-mini-tts",
      "voice": "alloy",
      "speed": 1.0,
      "sample_rate": 16000,
      "response_format": "pcm",
      "instruction": "calm",
      "enable_request_id": false
    }
  }

• Authenticate using params.api_key

  "tts": {
    "vendor": "generic_http",
    "url": "https://your-tts-service.example.com/v1/audio/speech",
    "params": {
      "api_key": "your_tts_api_key",
      "model": "gpt-4o-mini-tts",
      "voice": "alloy",
      "speed": 1.0,
      "sample_rate": 16000,
      "response_format": "pcm",
      "instruction": "calm",
      "enable_request_id": false
    }
  }

  If you provide both tts.headers.Authorization and tts.params.api_key, the Conversational AI Engine uses tts.headers.Authorization.

Key parameters

ttsrequired

urlstring

required

The OpenAI TTS protocol compatible service endpoint.

headersobject

optional

Custom request headers to include in requests to the TTS service, such as authentication credentials. Provide at least one of headers.Authorization or params.api_key. If you provide both, the Conversational AI Engine uses headers.Authorization.

paramsobject

required

api_keystring

optional

The API key used to authenticate with the TTS service. Provide at least one of headers.Authorization or params.api_key. If you provide both, the Conversational AI Engine uses headers.Authorization.

modelstring

optional

The name of the TTS model.

voicestring

optional

The voice name. Omit this parameter if your TTS service does not support multiple voices.

speednumber

optional

The speech rate.

sample_rateinteger

optional

Default value

16000

The sample rate, in Hz, of the output audio. If your TTS service does not support multiple sample rates, make sure the sample rate of the returned audio matches this value.

response_formatstring

optional

Default value

pcm

The output audio format. Currently only pcm is supported.

instructionstring

optional

Instructions for voice style, emotion, or other playback directives.

enable_request_idboolean

optional

Default value

false

Whether to include request_id, request_seq_id, and request_end in the TTS request body.