CartesiaReleased on Oct 27, 2025

Sonic 3: Benchmarks, Pricing & Context Window

Sonic 3 is a text-to-speech model from Cartesia, released in October 2025.

Cartesia Sonic-3 with volume, speed, and emotion controls. Supports 42 languages with industry-leading latency.

Input
Text
Output
Audio

Sonic 3 pricing

Providers

Sonic 3 starts at $10.00 per million input tokens via Cartesia.

ProviderInput $/MOutput $/MMax InputMax OutputLatency sThroughputQuantInputOutput
Cartesia logoCartesia
$10.002.5K

Sonic 3 API

POST/v1/tts/synthesize

Run a request to see the response

Use it in your code

OpenAI-compatible endpoint through the LLM Stats gateway.

import requests

response = requests.post(
    "https://gateway.llm-stats.com/v1/tts/synthesize",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model_id": "sonic-3",
        "text": "Hello, this is a test.",
        "format": "mp3",
        "sample_rate": 24000,
    },
)

with open("output.mp3", "wb") as f:
    f.write(response.content)

Need an API key? Create one above in the playground, or read the API documentation.

Sonic 3 license

Sonic 3 is released under the Proprietary license, which restricts commercial use.

License
Proprietary
Non-commercial

Proprietary license - usage restrictions apply

FAQ

Common questions about Sonic 3.

Who created Sonic 3?

Sonic 3 was created by Cartesia.

What is the license for Sonic 3?

Sonic 3 is released under the Proprietary license.

Is Sonic 3 multimodal?

Yes, Sonic 3 is a multimodal model that can process both text and images as input.