converse-sdk 0.1.0

Headless Python SDK for the Trelis Converse realtime voice API.

converse-sdk

The headless Python SDK for the Trelis Converse realtime voice API. Use it for telephony bridges, services, evaluations and custom devices.

uv add converse-sdk

The session-loop fragment below assumes your media layer supplies mic_frame and play_audio, and your application supplies run_tool:

import os

from converse_sdk import ConverseMode, ConverseSession

session = await ConverseSession.connect(
    "wss://converse.trelis.com/ws",
    api_key=os.environ["CONVERSE_API_KEY"],
    mode=ConverseMode(
        instructions="Help callers with their orders.",
        greeting="Hello, how can I help?",
    ),
)

async with session:
    await session.send_audio(mic_frame)  # PCM16 little-endian mono at 16 kHz

    async for event in session.events():
        if event.type == "audio":
            play_audio(event.audio)  # Float32 mono at 16 kHz
        elif event.type == "tool_call":
            result = await run_tool(event.data["name"], event.data["args"])
            await session.send_tool_result(event.data["id"], result)

The SDK deliberately does not own capture, playback, pacing or echo cancellation. Live playback integrations must implement the playback contract.

See the complete Python reference and the Twilio bridge quickstart.

Proprietary software. All rights reserved.