Real-time Audio Stream (WebSocket)

import asyncio
import websockets
import json
import base64

WS_URL = "wss://mavi-backend.memories.ai/serve/ws/v2/audio-stream"
API_KEY = "sk-mavi-..."

async def stream_audio():
    params = (
        f"?provider=elevenlabs"
        f"&api_key={API_KEY}"
        f"&model_id=scribe_v2_realtime"
        f"&language_code=en"
    )

    async with websockets.connect(WS_URL + params) as ws:
        # Start receiving task
        async def receive():
            async for message in ws:
                data = json.loads(message)
                print(json.dumps(data, indent=2))

        recv_task = asyncio.create_task(receive())

        # Send audio chunks (16kHz, 16-bit, mono PCM)
        with open("audio.pcm", "rb") as f:
            while chunk := f.read(3200):  # 100ms chunks
                msg = json.dumps({
                    "message_type": "input_audio_chunk",
                    "audio_base_64": base64.b64encode(chunk).decode(),
                    "commit": False,
                    "sample_rate": 16000
                })
                await ws.send(msg)
                await asyncio.sleep(0.1)

        # Send commit to finalize
        await ws.send(json.dumps({
            "message_type": "input_audio_chunk",
            "audio_base_64": "",
            "commit": True
        }))

        await recv_task

asyncio.run(stream_audio())

import asyncio
import websockets
import json

WS_URL = "wss://mavi-backend.memories.ai/serve/ws/v2/audio-stream"
API_KEY = "sk-mavi-..."

async def stream_audio():
    params = (
        f"?provider=assemblyai"
        f"&api_key={API_KEY}"
        f"&sample_rate=16000"
    )

    async with websockets.connect(WS_URL + params) as ws:
        # Start receiving task
        async def receive():
            async for message in ws:
                data = json.loads(message)
                print(json.dumps(data, indent=2))

        recv_task = asyncio.create_task(receive())

        # Send raw PCM binary frames (16kHz, 16-bit, mono)
        with open("audio.pcm", "rb") as f:
            while chunk := f.read(3200):  # 100ms chunks
                await ws.send(chunk)
                await asyncio.sleep(0.1)

        # Send termination
        await ws.send(json.dumps({"type": "session_termination"}))

        await recv_task

asyncio.run(stream_audio())

const WS_URL = 'wss://mavi-backend.memories.ai/serve/ws/v2/audio-stream';
const API_KEY = 'sk-mavi-...';

const params = new URLSearchParams({
    provider: 'elevenlabs',
    api_key: API_KEY,
    model_id: 'scribe_v2_realtime',
    language_code: 'en'
});

const ws = new WebSocket(`${WS_URL}?${params}`);

ws.onmessage = (event) => {
    const data = JSON.parse(event.data);
    console.log('Transcription:', JSON.stringify(data, null, 2));
};

ws.onopen = () => {
    console.log('Connected');

    // Example: send audio from MediaRecorder or file
    // Audio must be 16kHz, 16-bit, mono PCM, base64-encoded
    const sendChunk = (pcmBuffer) => {
        const base64 = btoa(String.fromCharCode(...new Uint8Array(pcmBuffer)));
        ws.send(JSON.stringify({
            message_type: 'input_audio_chunk',
            audio_base_64: base64,
            commit: false,
            sample_rate: 16000
        }));
    };

    // When done, send commit
    const finalize = () => {
        ws.send(JSON.stringify({
            message_type: 'input_audio_chunk',
            audio_base_64: '',
            commit: true
        }));
    };
};

ws.onerror = (err) => console.error('WebSocket error:', err);
ws.onclose = (event) => console.log('Closed:', event.code, event.reason);