Graph通話ボット

public class SpeechService
{
    private readonly AppSettings _settings;
    private readonly ILogger _logger;
    private ClientWebSocket _ws;
    private bool _started;
    private bool _connecting;
    public event EventHandler<MediaStreamEventArgs> SendMediaBuffer; // agent audio -> call
    public event EventHandler FlushMedia;                            // barge-in: drop queued audio
    public SpeechService(AppSettings settings, ILogger logger) { _settings = settings; _logger = logger; }
    // Caller audio -> ElevenLabs
    public async Task AppendAudioBuffer(AudioMediaBuffer buffer)
    {
        if (!_started)
        {
            if (_connecting) return;            // a connect attempt is already in flight
            _connecting = true;
            try { await Connect(); _started = true; }
            catch (Exception ex) { _logger.Error(ex, "ElevenLabs connect failed; retry on next frame"); return; }
            finally { _connecting = false; }
        }
        if (_ws?.State != WebSocketState.Open || buffer.Length <= 0) return;
        var pcm = new byte[buffer.Length];
        Marshal.Copy(buffer.Data, pcm, 0, (int)buffer.Length);
        var msg = JsonSerializer.Serialize(new { user_audio_chunk = Convert.ToBase64String(pcm) });
        await _ws.SendAsync(Encoding.UTF8.GetBytes(msg), WebSocketMessageType.Text, true, default);
    }
    private async Task Connect()
    {
        _ws = new ClientWebSocket();
        // ElevenLabsOrigin: wss://api.elevenlabs.io, or a residency host (.eu./.in./.sg.)
        var url = $"{_settings.ElevenLabsOrigin}/v1/convai/conversation?agent_id={_settings.ElevenLabsAgentId}";
        await _ws.ConnectAsync(new Uri(url), default);
        await _ws.SendAsync(Encoding.UTF8.GetBytes(
            JsonSerializer.Serialize(new { type = "conversation_initiation_client_data" })),
            WebSocketMessageType.Text, true, default);
        _ = Task.Run(ReceiveLoop);
    }
    private async Task ReceiveLoop()
    {
        var buf = new byte[32768]; var sb = new StringBuilder();
        while (_ws.State == WebSocketState.Open)
        {
            sb.Clear(); WebSocketReceiveResult r;
            do { r = await _ws.ReceiveAsync(buf, default); sb.Append(Encoding.UTF8.GetString(buf, 0, r.Count)); }
            while (!r.EndOfMessage);
            using var doc = JsonDocument.Parse(sb.ToString());
            var type = doc.RootElement.GetProperty("type").GetString();
            if (type == "audio")            // ElevenLabs audio -> call
                Emit(Convert.FromBase64String(doc.RootElement
                    .GetProperty("audio_event").GetProperty("audio_base_64").GetString()));
            else if (type == "ping")
                await _ws.SendAsync(Encoding.UTF8.GetBytes(JsonSerializer.Serialize(new {
                    type = "pong", event_id = doc.RootElement.GetProperty("ping_event").GetProperty("event_id").GetInt32() })),
                    WebSocketMessageType.Text, true, default);
            else if (type == "interruption")  // barge-in: drop any agent audio still queued
                FlushMedia?.Invoke(this, EventArgs.Empty);
        }
    }
    // slice PCM into 20 ms / 640-byte frames the media platform expects
    private void Emit(byte[] pcm)
    {
        var all = new List<AudioMediaBuffer>(); long tick = DateTime.Now.Ticks;
        for (int off = 0; off < pcm.Length; off += 640)
        {
            var frame = new byte[640];
            Array.Copy(pcm, off, frame, 0, Math.Min(640, pcm.Length - off));
            all.AddRange(Utilities.CreateAudioMediaBuffers(frame, tick, _logger));
            tick += 20 * 10000;
        }
        if (all.Count > 0) SendMediaBuffer?.Invoke(this, new MediaStreamEventArgs { AudioMediaBuffers = all });
    }
}

public class ChatBot : ActivityHandler
{
    private readonly AppSettings _settings;
    public ChatBot(AppSettings settings) => _settings = settings;
    protected override async Task OnMessageActivityAsync(
        ITurnContext<IMessageActivity> turn, CancellationToken ct)
    {
        var reply = await AskAgent(turn.Activity.Text, ct);
        await turn.SendActivityAsync(MessageFactory.Text(reply), ct);
    }
    private async Task<string> AskAgent(string text, CancellationToken ct)
    {
        using var ws = new ClientWebSocket();
        var url = $"{_settings.ElevenLabsOrigin}/v1/convai/conversation?agent_id={_settings.ElevenLabsAgentId}";
        await ws.ConnectAsync(new Uri(url), ct);
        // Suppress the agent's greeting: with no override, the first agent_response is the
        // configured first message, not the answer to this user_message.
        await Send(ws, new
        {
            type = "conversation_initiation_client_data",
            conversation_config_override = new { agent = new { first_message = "" } },
        }, ct);
        await Send(ws, new { type = "user_message", text }, ct);
        var buf = new byte[16384]; var sb = new StringBuilder();
        while (ws.State == WebSocketState.Open)
        {
            sb.Clear(); WebSocketReceiveResult r;
            do { r = await ws.ReceiveAsync(buf, ct); sb.Append(Encoding.UTF8.GetString(buf, 0, r.Count)); }
            while (!r.EndOfMessage);
            using var doc = JsonDocument.Parse(sb.ToString());
            switch (doc.RootElement.GetProperty("type").GetString())
            {
                case "agent_response":
                    return doc.RootElement.GetProperty("agent_response_event")
                              .GetProperty("agent_response").GetString();
                case "ping":
                    await Send(ws, new { type = "pong", event_id = doc.RootElement
                        .GetProperty("ping_event").GetProperty("event_id").GetInt32() }, ct);
                    break;
            }
        }
        return "Sorry, I couldn't reach the agent.";
    }
    private static Task Send(ClientWebSocket ws, object msg, CancellationToken ct) =>
        ws.SendAsync(Encoding.UTF8.GetBytes(JsonSerializer.Serialize(msg)),
            WebSocketMessageType.Text, true, ct);
}