Skip to main content

Usage guide

Setup, environment variables, and Python/JavaScript/Go usage examples.

​
InworldAITTS

Inworld AI TTS provider: realtime, low-latency text-to-speech via Inworld’s voice API. Wraps Inworld AI’s POST /tts/v1/voice endpoint. Supports both quality-optimised and latency-optimised model variants, instant voice cloning, and multilingual output. Audio is returned as base64-encoded MP3 by default; sample_rate controls the advertised output rate.

​
Constructor

​
api_key
str | None
Inworld AI API key. Falls back to the INWORLDAI_API_KEY environment variable when None.
​
voice_id
str
default:"Hades"
Voice identifier for synthesis. Use any voice ID available in the Inworld AI voice library (e.g. "Hades", "Sarah"), or a custom voice UUID obtained from the /voices/v1/voices:clone endpoint. Voice IDs are consistent across the TTS API and the Inworld Playground. Defaults to "Hades".
​
model_id
str
default:"inworld-tts-1"
TTS model to use. Options include "inworld-tts-1.5-max" (optimised for quality) and "inworld-tts-1.5-mini" (~120 ms median latency, optimised for speed). Defaults to "inworld-tts-1".
​
sample_rate
int
default:"24000"
Output audio sample rate in Hz. The API supports values in the range 8000–48000 Hz via the sampleRateHertz audio config field. Defaults to 24000.

​
aclose

Release any resources held by the provider.

​
emit

Emit an event, invoking all registered handlers with the given arguments. Handlers are called in registration order. Coroutine handlers are scheduled on the running event loop. If the emitter is closed, the call is a no-op.
​
event
T
required
The event to emit.

​
interrupt

Interrupt and cancel the current synthesis for the active session, if any.

​
off

Remove a previously registered handler for an event. If the handler is not registered for the event, the call is a no-op.
​
event
T
required
The event the handler was registered for.
​
callback
Callable[..., Any]
required
The handler to remove.

​
on

Register a handler for an event. Can be used directly by passing a callback, or as a decorator when callback is omitted.
​
event
T
required
The event to listen for.
​
callback
Callable[..., Any] | None
The handler to invoke when the event is emitted. If None, a decorator is returned that registers the decorated function.
​
returns
Callable[..., Any]
The registered callback when callback is provided, otherwise a decorator that registers and returns the function it wraps.

​
on_first_audio_byte

Register the callback invoked when the first audio byte is produced.
​
callback
'Callable[[int, int], Awaitable[None] | None]'
required
A callable, optionally async, invoked with synthesis timing information when the first audio byte is emitted.

​
synthesize

Synthesize the given text into speech. Implementations should convert the text to audio. The default behavior forwards the text to the active session for playback when one is present.
​
text
Any
required
The text to synthesize; coerced to a string if needed.