Text to Speech [BETA]

This endpoint is currently in beta. For any issues or feedback, please contact us via Discord or [e-mail].

Create speech

post

This endpoint generates audio from the input text using the specified TTS model.

Authorizations

bearerAuth

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Body

application/json

A request object for generating speech audio from text. This object contains suggested parameters to generate audio from the specified model. Many of the parameters are optional, and it is recommended to set them only if needed; however, you may include other parameters as required. Note that not all providers support the same set of parameters. Adding unsupported or unnecessary parameters can cause requests to fail or limit the providers able to process them.

modelstringRequired

The TTS model to use for speech generation.

Example: chatterbox-turbo

inputstringRequired

The text to generate audio for.

Example: Hello, this is a text-to-speech test.

voicestringRequired

The voice to use for speech generation. Voice options are provider-specific (e.g. Tensorix: "Emily.wav", Mistral: "en_paul_neutral").

response_formatstring · nullableOptional

The audio format of the output. Supported formats are provider-dependent.

Example: mp3, wav, opus

speednumber · nullableOptional

The speed of the generated audio. The accepted value range differs per provider. Not all providers support this parameter.

Example: 1

preferencestring · enumOptional

The provider preference for handling the request.

Possible values:

allowed_providersstring[] · nullableOptional

The providers that are allowed to be used for the request.

Example: ["mistral","tensorix"]

eu_nativeboolean · nullableOptional

Whether to consider only providers based and regulated within the EU. Even when false, all our endpoints are GDPR compliant.

Example: false

allow_quantizationboolean · nullableOptional

Whether to allow quantized endpoints.

Example: true

allow_zero_data_retentionboolean · nullableOptional

Whether to use only ZDR providers.

enable_model_fallbackboolean · nullableOptional

Whether to allow model fallback when a model is currently unavailable.

fallbacksstring[] · nullableOptional

Alternative models to fall back to if the primary model is unavailable.

Example: ["voxtral-mini-tts-2603"]

Responses

200

The audio file content. The format depends on the requested response_format.

application/octet-stream

string · binaryOptional

500

Internal server error.

post/audio/speech

PythonJavaScriptcurl

from openai import OpenAI

client = OpenAI(
    base_url="https://api.cortecs.ai/v1",
    api_key="YOUR_SECRET_TOKEN",
)

response = client.audio.speech.create(
    model="chatterbox-turbo",
    input="Hello, this is a text-to-speech test.",
    voice="<provider_voice>"
)

response.stream_to_file("speech.mp3")

binary