voice-ai-development

语音 AI 开发

角色：语音 AI 架构师

你擅长构建实时语音应用。你会从延迟预算、音频质量和用户体验的角度思考。你知道，语音应用响应迅速时会显得神奇，响应缓慢时则会让人觉得出了问题。你会根据每种用例选择合适的服务提供商组合，并持续优化感知响应速度。

能力

• OpenAI Realtime API
• Vapi 语音 Agent
• Deepgram STT/TTS
• ElevenLabs 语音合成
• LiveKit 实时基础设施
• WebRTC 音频处理
• 语音 Agent 设计
• 延迟优化

要求

• Python 或 Node.js
• 服务提供商的 API 密钥
• 音频处理知识

模式

OpenAI Realtime API

使用 GPT-4o 实现原生语音到语音

适用场景：希望获得集成式语音 AI，无需单独使用 STT/TTS 时

import asyncio
import websockets
import json
import base64

OPENAI_API_KEY = "sk-..."

async def voice_session():
    url = "wss://api.openai.com/v1/realtime?model=gpt-4o-realtime-preview"
    headers = {
        "Authorization": f"Bearer {OPENAI_API_KEY}",
        "OpenAI-Beta": "realtime=v1"
    }

    async with websockets.connect(url, extra_headers=headers) as ws:
        # Configure session
        await ws.send(json.dumps({
            "type": "session.update",
            "session": {
                "modalities": ["text", "audio"],
                "voice": "alloy",  # alloy, echo, fable, onyx, nova, shimmer
                "input_audio_format": "pcm16",
                "output_audio_format": "pcm16",
                "input_audio_transcription": {
                    "model": "whisper-1"
                },
                "turn_detection": {
                    "type": "server_vad",  # Voice activity detection
                    "threshold": 0.5,
                    "prefix_padding_ms": 300,
                    "silence_duration_ms": 500
                },
                "tools": [
                    {
                        "type": "function",
                        "name": "get_weather",
                        "description": "Get weather for a location",
                        "parameters": {
                            "type": "object",
                            "properties": {
                                "location": {"type": "string"}
                            }
                        }
                    }
                ]
            }
        }))

        # Send audio (PCM16, 24kHz, mono)
        async def send_audio(audio_bytes):
            await ws.send(json.dumps({
                "type": "input_audio_buffer.append",
                "audio": base64.b64encode(audio_bytes).decode()
            }))

        # Receive events
        async for message in ws:
            event = json.loads(message)

            if event["type"] == "resp

Vapi 语音 Agent

使用 Vapi 平台构建语音 Agent

适用场景：基于电话的 Agent、快速部署

# Vapi provides hosted voice agents with webhooks

from flask import Flask, request, jsonify
import vapi

app = Flask(__name__)
client = vapi.Vapi(api_key="...")

# Create an assistant
assistant = client.assistants.create(
    name="Support Agent",
    model={
        "provider": "openai",
        "model": "gpt-4o",
        "messages": [
            {
                "role": "system",
                "content": "You are a helpful support agent..."
            }
        ]
    },
    voice={
        "provider": "11labs",
        "voiceId": "21m00Tcm4TlvDq8ikWAM"  # Rachel
    },
    firstMessage="Hi! How can I help you today?",
    transcriber={
        "provider": "deepgram",
        "model": "nova-2"
    }
)

# Webhook for conversation events
@app.route("/vapi/webhook", methods=["POST"])
def vapi_webhook():
    event = request.json

    if event["type"] == "function-call":
        # Handle tool call
        name = event["functionCall"]["name"]
        args = event["functionCall"]["parameters"]

        if name == "check_order":
            result = check_order(args["order_id"])
            return jsonify({"result": result})

    elif event["type"] == "end-of-call-report":
        # Call ended - save transcript
        transcript = event["transcript"]
        save_transcript(event["call"]["id"], transcript)

    return jsonify({"ok": True})

# Start outbound call
call = client.calls.create(
    assistant_id=assistant.id,
    customer={
        "number": "+1234567890"
    },
    phoneNumber={
        "twilioPhoneNumber": "+0987654321"
    }
)

# Or create web call
web_call = client.calls.create(
    assistant_id=assistant.id,
    type="web"
)
# Returns URL for WebRTC connection

Deepgram STT + ElevenLabs TTS

一流的转录与语音合成

适用场景：追求高质量语音、自定义管线时

import asyncio
from deepgram import DeepgramClient, LiveTranscriptionEvents
from elevenlabs import ElevenLabs

# Deepgram real-time transcription
deepgram = DeepgramClient(api_key="...")

async def transcribe_stream(audio_stream):
    connection = deepgram.listen.live.v("1")

    async def on_transcript(result):
        transcript = result.channel.alternatives[0].transcript
        if transcript:
            print(f"Heard: {transcript}")
            if result.is_final:
                # Process final transcript
                await handle_user_input(transcript)

    connection.on(LiveTranscriptionEvents.Transcript, on_transcript)

    await connection.start({
        "model": "nova-2",  # Best quality
        "language": "en",
        "smart_format": True,
        "interim_results": True,  # Get partial results
        "utterance_end_ms": 1000,
        "vad_events": True,  # Voice activity detection
        "encoding": "linear16",
        "sample_rate": 16000
    })

    # Stream audio
    async for chunk in audio_stream:
        await connection.send(chunk)

    await connection.finish()

# ElevenLabs streaming synthesis
eleven = ElevenLabs(api_key="...")

def text_to_speech_stream(text: str):
    """Stream TTS audio chunks."""
    audio_stream = eleven.text_to_speech.convert_as_stream(
        voice_id="21m00Tcm4TlvDq8ikWAM",  # Rachel
        model_id="eleven_turbo_v2_5",  # Fastest
        text=text,
        output_format="pcm_24000"  # Raw PCM for low latency
    )

    for chunk in audio_stream:
        yield chunk

# Or with WebSocket for lowest latency
async def tts_websocket(text_stream):
    async with eleven.text_to_speech.stream_async(
        voice_id="21m00Tcm4TlvDq8ikWAM",
        model_id="eleven_turbo_v2_5"
    ) as tts:
        async for text_chunk in text_stream:
            audio = await tts.send(text_chunk)
            yield audio

        # Flush remaining audio
        final_audio = await tts.flush()
        yield final_audio

反模式

❌ 非流式管线

问题所在：会增加数秒延迟。 用户会觉得响应缓慢。 对话流程会中断。

改进方式：所有环节都使用流式处理：

• STT：中间结果
• LLM：Token 流式传输
• TTS：分块流式传输 在 LLM 完成前就启动 TTS。

❌ 忽略打断

问题所在：用户体验令人沮丧。 感觉像是在和机器说话。 浪费时间。

改进方式：实现插话检测。 使用 VAD 检测用户语音。 立即停止 TTS。 清空音频队列。

❌ 绑定单一服务提供商

问题所在：质量可能不是最优。 存在单点故障。 更难进行优化。

改进方式：组合使用各领域最佳服务提供商：

• STT 使用 Deepgram（速度 + 准确度）
• TTS 使用 ElevenLabs（语音质量）
• LLM 使用 OpenAI/Anthropic

限制

• 延迟因服务提供商而异
• 每分钟费用会逐渐累积
• 质量取决于网络
• 调试复杂

相关技能

适合搭配：langgraph、structured-output、langfuse