livekit-plugins-readaloud

ReadAloud text-to-speech plugin for LiveKit Agents. Status: alpha, unpublished (see ../docs/STATUS_MATRIX.md).

pip install livekit-plugins-readaloud   # not yet on PyPI: install from this directory with `pip install .`
export READALOUD_API_KEY=rtts_...

from livekit.agents import AgentSession
from livekit.plugins import readaloud

session = AgentSession(
    # stt=..., llm=...,
    tts=readaloud.TTS(voice="default", sample_rate=24000),   # sample_rate: 24000 | 16000 | 8000
)

readaloud.TTS(api_key=None, base_url="https://api.readaloudai.org", voice="default", speed=1.0, engine="piper", sample_rate=24000, max_retries=2). synthesize() returns a ChunkedStream; stream() returns a SynthesizeStream that splits LLM tokens into sentences and synthesizes each with its own streaming request (sentence-level pipelining). Closing a stream (barge-in) closes the HTTP connection, which stops generation server-side. Capacity (503/429) becomes a retryable APIStatusError, so LiveKit's APIConnectOptions retry applies on top of the plugin's own pre-audio retries (set max_retries=0 to leave retrying to LiveKit). No aligned transcripts. Tested with livekit-agents==1.8.5; requires livekit-agents>=1.8,<2.

Tests: pip install -e '.[dev]' && pytest.