Newer
Older
cortex-hub / ai-hub / docs / api_reference / tts.md

API Reference: TTS

POST /speech

Summary: Generate speech from text

Description: Generate speech from text

Parameters

Name In Required Type Description
stream query No boolean If true, returns a streamed audio response. Otherwise, returns a complete file.
as_wav query No boolean If true, returns WAV format audio. If false, returns raw PCM audio data. Only applies when stream is true.
provider_name query No string Optional session-level override for the TTS provider
x-user-id header No anyOf

Request Body

Required: Yes

  • Media Type: application/json
  • Schema: SpeechRequest (Define in Models)

Responses

Status Code Description
200 Audio bytes in WAV or PCM format, either as a complete file or a stream.
422 Validation Error

Example Usage

curl -X 'POST' \
  'http://localhost:8000/api/v1/speech?stream=<stream>&as_wav=<as_wav>&provider_name=<provider_name>' \
  -H 'accept: application/json' \
  -H 'X-User-ID: <your_user_id>' \
  -H 'Content-Type: application/json' \
  -d '{}'

GET /speech/voices

Summary: List available TTS voices

Description: List available TTS voices

Parameters

Name In Required Type Description
provider query No string Optional provider name
api_key query No string Optional API key override
x-user-id header No anyOf

Responses

Status Code Description
200 A list of voice names
422 Validation Error

Example Usage

curl -X 'GET' \
  'http://localhost:8000/api/v1/speech/voices?provider=<provider>&api_key=<api_key>' \
  -H 'accept: application/json' \
  -H 'X-User-ID: <your_user_id>'