Quickstart

1. Create an Account

2. Generate an API Key

Go to API Keys in your dashboard
Click Create API Key
Copy the key — it starts with sk_996_ and is only shown once

3. Add Credits

The API is pay-as-you-go. Head to Billing and top up (minimum $5 — $5 buys 1,000,000 characters). 1 credit = 1 character of input.

4. Make Your First Request

curl

curl -N https://api.nineninesix.ai/tts/bytes \
  -H "Authorization: Bearer sk_996_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model_id": "gepard-1.0",
    "transcript": "Welcome to Nineninesix!",
    "voice": { "mode": "id", "id": "<voice-id>" },
    "output_format": { "container": "wav", "encoding": "pcm_s16le", "sample_rate": 22050 }
  }' --output welcome.wav

Python

from cartesia import Cartesia

client = Cartesia(
    api_key="sk_996_your_api_key",
    base_url="https://api.nineninesix.ai",
)

audio = client.tts.bytes(
    model_id="gepard-1.0",
    transcript="Welcome to Nineninesix!",
    voice={"mode": "id", "id": "<voice-id>"},
    output_format={"container": "wav", "encoding": "pcm_s16le", "sample_rate": 22050},
)

with open("welcome.wav", "wb") as f:
    f.write(audio)

Node.js

import { Cartesia } from "@cartesia/cartesia-js";

const client = new Cartesia({
  apiKey: "sk_996_your_api_key",
  baseURL: "https://api.nineninesix.ai",
});

const res = await client.tts.generate({
  model_id: "gepard-1.0",
  transcript: "Welcome to Nineninesix!",
  voice: { mode: "id", id: "<voice-id>" },
  output_format: { container: "wav", encoding: "pcm_s16le", sample_rate: 22050 },
});

const buffer = Buffer.from(await res.arrayBuffer());
await fs.promises.writeFile("welcome.wav", buffer);

5. Find a Voice

List available voices with GET /voices, or browse them in the Playground. Use a voice's id in the voice field.

Next Steps

Explore the TTS Playground in your dashboard
Read the full API Reference
Stream in real time with the WebSocket endpoint