Text-to-Speech API Quickstart

import requests

# Using default voice (voice_id is optional)
response = requests.post(
    'https://dev.voice.ai/api/v1/tts/speech/stream',
    headers={'Authorization': 'Bearer YOUR_API_KEY', 'Content-Type': 'application/json'},
    json={
        'text': 'This text will be streamed in chunks.',
        'model': 'voiceai-tts-v1-latest',  # Optional, defaults to voiceai-tts-v1-latest
        'language': 'en'  # Optional, defaults to 'en'
    },
    stream=True
)

# Or with a custom voice_id:
# json={'voice_id': 'your-voice-id-here', 'text': 'This text will be streamed in chunks.', 'model': 'voiceai-tts-v1-latest', 'language': 'en'}

with open('output.mp3', 'wb') as f:
    for chunk in response.iter_content():
        if chunk: f.write(chunk)

import asyncio
import json
import base64
import websockets

async def tts_conversation():
    # Use /multi-stream for multiple generations over persistent connection
    url = "wss://dev.voice.ai/api/v1/tts/multi-stream"
    headers = {"Authorization": "Bearer YOUR_API_KEY"}
    
    async with websockets.connect(url, additional_headers=headers) as ws:
        # First message (context auto-generated)
        await ws.send(json.dumps({
            "text": "Hello! How can I help you today?",
            "language": "en",
            "flush": True
        }))
        
        # Receive audio chunks
        while True:
            msg = await ws.recv()
            data = json.loads(msg)
            if data.get("audio"):
                audio_chunk = base64.b64decode(data["audio"])
                # Process/play audio chunk...
            elif data.get("is_last"):
                break
        
        # Second generation (same connection)
        await ws.send(json.dumps({
            "text": "I can help you with that.",
            "flush": True
        }))
        
        # Receive audio...
        while True:
            msg = await ws.recv()
            data = json.loads(msg)
            if data.get("audio"):
                audio_chunk = base64.b64decode(data["audio"])
                # Process/play audio chunk...
            elif data.get("is_last"):
                break
        
        # Close when done
        await ws.send(json.dumps({"close_socket": True}))

asyncio.run(tts_conversation())