Other integrations

Use the Python SDK or Node SDK for any async PCM16 audio stream.

async with Openspline().avatar("portrait.jpg") as avatar:
    print(avatar.viewer_url)
    await avatar.stream(agent.audio_stream(), sample_rate=24000)

For callbacks, call send_audio() for each chunk, then end_turn() when speech ends and interrupt() on barge in.

Integration	Runnable example
Pipecat	Python bot
Google ADK	Python agent
Vocode	Vocode app
TEN	TEN graph
Any audio source	Python universal · Node universal

The Python examples have locked dependencies. Vocode uses its own lockfile.

Start here

Build an avatar

Connect your agent

Reference