Speech Enhancement

import asyncio
import base64
import json
import os
import wave

import websockets

URL = "wss://api.kugelaudio.com/v1/audio/enhance/stream"

async def main():
    headers = {"Authorization": f"Bearer {os.environ['KUGELAUDIO_API_KEY']}"}
    speaker = open("speaker.wav", "rb").read()
    out = bytearray()

    with wave.open("meeting.wav", "rb") as src:  # mono, 16-bit
        rate = src.getframerate()
        async with websockets.connect(URL, additional_headers=headers) as ws:
            await ws.send(json.dumps({
                "type": "config",
                "model": "clarity-1",
                "task": "target_speaker_extraction",
                "sample_rate_hz": rate,
                "encoding": "pcm_s16le",
                "speaker_wav_b64": base64.b64encode(speaker).decode(),
            }))
            ready = json.loads(await ws.recv())
            if ready["type"] != "ready":
                raise RuntimeError(ready)

            async def send():
                while chunk := src.readframes(rate // 5):  # 200 ms per message
                    await ws.send(chunk)
                await ws.send(json.dumps({"type": "end"}))

            sender = asyncio.create_task(send())
            async for message in ws:
                if isinstance(message, bytes):
                    out += message  # mono PCM16 at 24 kHz
                    continue
                event = json.loads(message)
                if event["type"] == "error":
                    raise RuntimeError(event)
                if event["type"] == "done":
                    break
            await sender

    with wave.open("one-voice.wav", "wb") as dst:
        dst.setnchannels(1)
        dst.setsampwidth(2)
        dst.setframerate(24000)
        dst.writeframes(bytes(out))

asyncio.run(main())

{"type": "error", "error": "Invalid request", "error_code": "VALIDATION_ERROR", "code": 400, "request_id": "9f2c1b7e4a6d4c8fb0e5a3d719c26f84"}