Usage guide
Setup, environment variables, and Python/JavaScript/Go usage examples.
SpeechifyTTS
Text-to-speech with Speechify’s Simba voices, using your own Speechify key. A simple choice for clear, natural English or multilingual narration. Authenticates with SPEECHIFY_API_KEY from your environment, or an explicitapi_key.
Fields
str
default:"UNSET"
Speechify voice ID, e.g. “kristy”. Defaults to ‘kristy’.
Literal['simba-base', 'simba-english', 'simba-multilingual', 'simba-turbo']
default:"UNSET"
Simba voice model: “simba-english”, “simba-multilingual”, “simba-base” or “simba-turbo”. Defaults to ‘simba-english’.
Optional[str]
default:"UNSET"
Language of the text, e.g. “en-US” or “fr-FR”. Mostly useful with simba-multilingual. Defaults to None (not set).
Literal['mp3', 'ogg', 'aac']
default:"UNSET"
Output audio format: “mp3”, “ogg” or “aac”. Defaults to ‘mp3’.
Optional[bool]
default:"UNSET"
Whether output volume is normalized to a consistent loudness. Leave unset to let Speechify decide. Defaults to None (not set).
Optional[bool]
default:"UNSET"
Whether numbers, dates and abbreviations are expanded into spoken words. Leave unset to let Speechify decide. Defaults to None (not set).
bool
default:"UNSET"
Synthesize each sentence as soon as it is ready instead of the whole reply at once. Faster first audio for long replies, at some cost to natural flow. Defaults to False.