Stream audio on Cloud

Create a key in the Cloud dashboard. Keep it on your backend.

pip install openspline
export OPENSPLINE_API_KEY="YOUR_API_KEY"

from openspline import Openspline

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

Open the printed URL to watch playback. agent.audio_stream() is your async iterator of PCM16 chunks; sample_rate is in Hz. Use a portrait saved in the dashboard:

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

Pass avatar.session to your frontend. For Node, use the Node SDK.

Start here

Build an avatar

Connect your agent

Reference

Stream audio on Cloud