Gestion des tours de parole avec la VAD sémantique

def turn_has_probably_ended(msg):
    if msg["type"] != "step" or not msg["vad"]:
        return False
    horizon = msg["vad"][-1]
    return horizon["inactivity_prob"] > 0.5

import asyncio
import gradium


async def transcribe_turns(audio_source):
    client = gradium.client.GradiumClient(api_key="your-api-key")

    async with client.stt_realtime(
        model_name="default",
        input_format="pcm",
        json_config={"language": "en", "delay_in_frames": 16},
    ) as stt:
        transcript = []
        high_vad_steps = 0

        async def producer():
            async for chunk in audio_source:
                await stt.send_audio(chunk)
            await stt.send_eos()

        async def consumer():
            nonlocal high_vad_steps, transcript

            async for msg in stt:
                if msg["type"] == "text":
                    transcript.append(msg["text"])

                elif msg["type"] == "step":
                    inactivity = msg["vad"][-1]["inactivity_prob"]
                    high_vad_steps = high_vad_steps + 1 if inactivity > 0.5 else 0

                    if high_vad_steps >= 3 and transcript:
                        await stt.send_flush(flush_id=1)

                elif msg["type"] == "flushed":
                    text = " ".join(transcript).strip()
                    transcript = []
                    high_vad_steps = 0
                    await handle_user_turn(text)

                elif msg["type"] == "end_of_stream":
                    return

        await asyncio.gather(producer(), consumer())