Skip to main content

Usage guide

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

​
GroqTTS

Groq TTS provider: low-latency text-to-speech via Groq’s inference API. Wraps the OpenAI-compatible /openai/v1/audio/speech endpoint served by Groq. Supports the PlayAI Dialog (playai-tts) and Canopy Labs Orpheus (canopylabs/orpheus-v1-english, canopylabs/orpheus-arabic-saudi) model families with streaming WAV output.

​
Constructor

​
api_key
str | None
Groq API key. Falls back to the GROQ_API_KEY environment variable when None.
​
model
str
default:"playai-tts"
TTS model identifier. Current options include "playai-tts" (PlayAI Dialog v1.0, English), "playai-tts-arabic" (PlayAI Dialog v1.0, Arabic), "canopylabs/orpheus-v1-english" (Orpheus English with vocal direction support), and "canopylabs/orpheus-arabic-saudi" (Orpheus Arabic, Saudi dialect). Defaults to "playai-tts".
​
voice
str
default:"Fritz-PlayAI"
Voice identifier to use for synthesis. For the playai-tts model, example voices include "Fritz-PlayAI", "Aaliyah-PlayAI", and "Adelaide-PlayAI". For the Orpheus English model, available voices include "troy", "hannah", "austin", "diana", "autumn", and "daniel". Defaults to "Fritz-PlayAI".
​
speed
float
default:"1.0"
Speaking speed multiplier. Defaults to 1.0 (normal pace).
​
response_format
str
default:"wav"
Audio container format for the returned audio. Defaults to "wav".
​
sample_rate
int
default:"24000"
Output audio sample rate in Hz. 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.