Usage guide
Setup, environment variables, and Python/JavaScript/Go usage examples.
ResembleTTS
Text-to-speech with Resemble AI voices, including your own cloned voices and the Chatterbox models. Choose it when you need custom or cloned voices. Authenticates with RESEMBLE_API_KEY from your environment, or an explicitapi_key.
Fields
str
default:"UNSET"
UUID of the Resemble voice to speak with, from your Resemble account. Defaults to ‘55592656’.
int
default:"UNSET"
Sample rate in Hz of the generated audio, e.g. 16000, 22050, 32000 or 44100. Defaults to 22050.
str
default:"UNSET"
Bit depth of the generated audio, e.g. “PCM_16” or “PCM_32”. Defaults to ‘PCM_16’.
Optional[str]
default:"UNSET"
Resemble model to synthesize with, e.g. “chatterbox” or “chatterbox-turbo”. Leave unset to use your account’s model. Defaults to None (not set).