Skip to main content

​
Rime TTS

RimeTTS targets the Rime HTTP endpoint. Both Arcana (high fidelity) and Mist (low latency) model families are supported. The provider requests audio/pcm and yields raw PCM_S16LE chunks at the configured sample rate.

​
Install

pip install "patter[rime]"

​
Usage

from patter.providers.rime_tts import RimeTTS

# Arcana — highest quality, up to 4-minute request timeout.
tts = RimeTTS(
    api_key="...",           # or RIME_API_KEY env var
    model="arcana",
    speaker="astra",
    lang="eng",
    sample_rate=16000,
)

# Mist v2 — low-latency, streaming-friendly.
fast = RimeTTS(
    model="mistv2",
    speaker="cove",
    speed_alpha=1.1,
    reduce_latency=True,
)

async for chunk in tts.synthesize("Ciao dal Patter pipeline."):
    ...

await tts.close()

​
Options (selection)

OptionDefaultNotes
model"arcana""arcana" or any mist* model.
speaker"astra" / "cove"Default depends on model.
lang"eng"Rime language code.
sample_rate16000Hz.
temperature, top_p, max_tokens, repetition_penalty—Arcana only.
speed_alpha, reduce_latency, pause_between_brackets, phonemize_between_brackets—Mist only.

​
Attribution

Ported from LiveKit Agents (livekit-plugins-rime, Apache License 2.0).