Quickstart

curl -X POST "https://api.vogent.ai/tts" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "So I tried this new thing called Voicelab that I found online, and the voices that it generated were super realistic.",
    "voiceId": "23b2186b-ed56-4185-998c-8d19e1bb227a"
  }' \
  --output my-first-voice.wav

import requests

api_key = "YOUR_API_KEY"

# Create a conversation between two people
conversation = {
    "lines": [
        {
            "text": "So I tried this new thing called Voicelab that I found online, and the voices that it generated were super realistic.",
            "voiceId": "23b2186b-ed56-4185-998c-8d19e1bb227a"  # The CSM-1B professional voice clone "Mabel"
        },
        {
            "text": "That's interesting, was it actually like super realistic or was it just not robotic.",
            "voiceId": "50c9287d-bcee-4f2a-943f-f0f2184a5d3b"  # The CSM-1B professional voice clone "Kevin"
        },
        {
            "text": "I mean, it's hard to tell the difference from a real person speaking. The technology is incredible.",
            "voiceId": "23b2186b-ed56-4185-998c-8d19e1bb227a"  # The CSM-1B professional voice clone "Mabel"
        },
        {
            "text": "Interesting, I've been looking for a new API to use in my app. I'll definitely check it out then.",
            "voiceId": "50c9287d-bcee-4f2a-943f-f0f2184a5d3b"  # The CSM-1B professional voice clone "Kevin"
        }
    ]
}

response = requests.post(
    "https://api.vogent.ai/tts/multispeaker",
    headers={"Authorization": f"Bearer {api_key}"},
    json=conversation
)

if response.status_code == 200:
    with open("conversation.wav", "wb") as f:
        f.write(response.content)
    print("✅ Conversation saved as 'conversation.wav'")
else:
    print(f"❌ Error: {response.status_code}")

import asyncio
import websockets
import json
import base64
import uuid
import wave

SAMPLE_RATE = 24000
API_KEY = ""
async def stream_tts():
    # Connect to the WebSocket endpoint
    uri = f"wss://api.vogent.ai/api/tts/websocket?apiKey={API_KEY}"
    generation_id = f"gen_{uuid.uuid4()}"

    async with websockets.connect(uri) as websocket:
        print("🔗 Connected to Voicelab WebSocket")

        # Send initial text chunk
        await websocket.send(json.dumps({
            "generationId": generation_id,
            "voiceId": "36b87413-6d7b-421d-8745-bc0897770d1e",  # Mabel voice
            "text": "Hello! This is a real-time streaming example.",
            "finalText": False,
            "sampleRate": 24000,
            "cancel": False
        }))

        # Send final text chunk
        await websocket.send(json.dumps({
            "generationId": generation_id,
            "voiceId": "36b87413-6d7b-421d-8745-bc0897770d1e",
            "text": " This demonstrates real-time text-to-speech streaming!",
            "finalText": True,
            "cancel": False
        }))

        audio_chunks = []

        print("Listening for audio")
        # Listen for audio chunks
        async for message in websocket:
            data = json.loads(message)

            if data["type"] == "chunk":
                # Decode and store audio chunk
                audio_data = base64.b64decode(data["audio"])
                audio_chunks.append(audio_data)
                print("🎵 Received audio chunk")

            elif data["type"] == "error":
                print(f"❌ Error: {data['error']}")
                break

            elif data["type"] == "finished":
                print("✅ Streaming complete!")

                with wave.open("streaming_audio.wav", "wb") as wf:
                    wf.setnchannels(1)
                    wf.setsampwidth(2)
                    wf.setframerate(SAMPLE_RATE)

                    print("Chunks", len(audio_chunks))
                    for chunk in audio_chunks:
                        wf.writeframes(chunk)

                print("💾 Audio saved as 'streaming_audio.wav'")
                break

# Run the streaming example
asyncio.run(stream_tts())