Skip to main content
The Python SDK and docs are currently in beta. Report issues on GitHub.
Text-to-speech request input

Fields

FieldTypeRequiredDescriptionExample
inputstr:heavy_check_mark:Text to synthesizeHello world
modelstr:heavy_check_mark:TTS model identifierelevenlabs/eleven-turbo-v2
providerOptional[components.SpeechRequestProvider]:heavy_minus_sign:Provider-specific passthrough configuration
response_formatOptional[components.ResponseFormatEnum]:heavy_minus_sign:Audio output formatpcm
speedOptional[float]:heavy_minus_sign:Playback speed multiplier. Only used by models that support it (e.g. OpenAI TTS). Ignored by other providers.1
voicestr:heavy_check_mark:Voice identifier (provider-specific).alloy