AssemblyAITTS
Low-latency streaming text-to-speech with AssemblyAI, using your own AssemblyAI key. One session serves the whole call, in English, Spanish, German, Italian, Portuguese and French, plus your own cloned voices. Authenticates with ASSEMBLYAI_API_KEY from your environment, or an explicitapi_key.
Fields
str
default:"UNSET"
TTS model. Defaults to ‘assemblyai-tts-1’.
str
default:"UNSET"
Voice slug or ID from the AssemblyAI catalog, or a cloned voice. Built-in voices such as the default start fastest, because they are always loaded. Defaults to ‘aai-jane’.
str | None
default:"UNSET"
English name of the language to speak: “english”, “spanish”, “german”, “italian”, “portuguese” or “french”. Leave unset to speak the voice’s own language. AssemblyAI does not detect it from the text. Defaults to None (not set).
str
default:"UNSET"
Data zone, “US” or “EU”. Use the one nearest the agent, and the same one as AssemblyAISTT. Ignored when base_url is set. Defaults to ‘US’.
str | None
default:"UNSET"
Streaming host override, e.g. “wss://tts.eu.assemblyai.com”. Overrides region. Defaults to None (not set).