Protobuf quickstart

uv init --python 3.11 coda-binary
cd coda-binary
uv add 'websockets>=15,<16' 'rime-api==0.0.1'

import asyncio
import os

from rime_api import text_to_speech_pb2 as proto
from websockets.asyncio.client import connect

URL = "wss://api.rime.ai/coda/ws"
CONTEXT_ID = "turn-1"


async def receive_event(connection):
    raw = await connection.recv()
    if not isinstance(raw, bytes):
        raise RuntimeError("Expected a Protobuf binary message")
    event = proto.WebSocketResponse.FromString(raw)
    if event.WhichOneof("payload") == "error":
        raise RuntimeError(f"Rime error: {event.error}")
    return event


async def send_sentences(connection):
    for sentence in ["Hello from Coda. ", "This audio uses the binary protocol. "]:
        request = proto.WebSocketRequest(context_id=CONTEXT_ID, text=sentence)
        await connection.send(request.SerializeToString())
    request = proto.WebSocketRequest(context_id=CONTEXT_ID)
    request.end.SetInParent()
    await connection.send(request.SerializeToString())


async def receive_audio(connection, output):
    while True:
        event = await receive_event(connection)
        if event.context_id != CONTEXT_ID:
            raise RuntimeError("Unexpected context ID")
        payload = event.WhichOneof("payload")
        if payload == "started":
            print("Request ID:", event.started.request_id)
        elif payload == "audio":
            output.write(event.audio)
        elif payload == "done":
            return
        elif payload == "cancelled":
            raise RuntimeError("Synthesis was cancelled")


async def main():
    headers = {"Authorization": f"Bearer {os.environ['RIME_API_KEY']}"}
    async with asyncio.timeout(120):
        async with connect(
            URL, additional_headers=headers, subprotocols=["rime.v1.binary"]
        ) as connection:
            if connection.subprotocol != "rime.v1.binary":
                raise RuntimeError("Binary subprotocol was not selected")
            event = await receive_event(connection)
            if event.WhichOneof("payload") != "ready" or event.ready.protocol != 1:
                raise RuntimeError("Expected WebSocket protocol version 1")
            request = proto.WebSocketRequest(
                context_id=CONTEXT_ID,
                start=proto.SynthesisRequest(
                    speaker="lyra",
                    language="en",
                    audio_parameters=proto.AudioParameters(
                        audio_format="audio/pcm", sampling_rate=24000
                    ),
                ),
            )
            await connection.send(request.SerializeToString())
            with open("output.pcm", "wb", buffering=0) as output:
                async with asyncio.TaskGroup() as tasks:
                    tasks.create_task(send_sentences(connection))
                    tasks.create_task(receive_audio(connection, output))
    print("Saved output.pcm")


if __name__ == "__main__":
    asyncio.run(main())

uv run stream_binary.py

uv run stream_binary.py

uv run python - <<'PY'
from importlib.resources import files
from pathlib import Path

schema = files("rime_api").joinpath("schema/rime/text_to_speech.proto")
Path("text_to_speech.proto").write_bytes(schema.read_bytes())
PY