Sent Voice Agents for Python

An AI agent that takes and places phone calls through Sent, on the Sent Voice Agents protocol 0.2.0.

Status: Preview, with the protocol. Generated and rendered by sent-dm-sdk-pipeline from the protocol at v0.2.0; every release passes the protocol's conformance scenarios in CI.

Read the Voice Agents docs to get started.

Install

pip install sentdm-voice-agents

Python 3.11 or later. The one dependency is websockets.

Quickstart

from sentdm_voice_agents import Agent, Session

class Support(Agent):
    async def on_session_start(self, session: Session) -> None:
        await session.say("Hi, this is Acme support. How can I help?")

    async def on_user_said(self, session: Session, said) -> None:
        if "person" in said.text:
            await session.say("Transferring you now.")
            await session.transfer("+14155550100")
        else:
            await session.say(f"You said {said.text}")

Support(api_key="sk_live_...", agent_id="agent_...").serve()

serve() connects to Sent with the account API key and serves calls until SIGINT or SIGTERM; await agent.run() does the same inside your own event loop. Each session's handlers run in order on their own task, so sessions never wait for one another. The runtime answers heartbeats, opens a new connection when one drains or is lost, and resumes the sessions that can move; the handlers only see calls.

Handler	When
on_session_start(session)	A call reached the agent. In a text session, say() to speak
on_user_said(session, said)	Text sessions: the caller said something; said.correction means it replaces the previous one
on_audio(session, samples)	Audio sessions: the caller's audio, 16-bit mono PCM at session.sample_rate
on_tool_result(session, result)	Sent answered a tool call; the awaiting call gets the same result
on_session_end(session, end)	The call left the agent; end.reason says why
on_session_lost(session)	The connection was lost and the session could not be resumed

On a Session: say(text, last=True, interruptible=True), clear(), send_audio(samples), and the tools transfer(to), hangup(), send_dtmf(digits), hold(held), each returning Sent's ToolResult. session.from_, to, direction, session_type, language, context, sample_rate carry what session.start said.

sentdm_voice_agents.frames holds every frame as a type, with decode() and encode() that check the protocol's rules; it is generated from the protocol and not edited by hand.

Develop

uv sync                     # the package and its test dependencies
uv run pytest               # the runtime and the frames against the protocol's fixtures

The conformance scenarios run in CI through the protocol's action, against python -m sentdm_voice_agents.conformance. Releases are cut by release-please from main and published to PyPI from GitHub Actions.