Capabilities
Explore what Sonic 3 (2026-01-12) supports, then use the API section for a request tailored to this model.
Languages
Model Information
- Provider
- Cartesia
- Product
- Text-to-Speech
- Release Date
- Jan 12, 2026
- Data Policy
- Not specified
- Region
- Global
- Input
- Text
- Output
- Audio
Playground
Try Sonic 3 (2026-01-12) by Cartesia. Requests use the selected workspace’s credits and API pricing.
Providers
Compare available endpoints, pricing, and context limits for Sonic 3 (2026-01-12).
| Provider | Context | Output | Input Price | Output Price | Endpoint |
|---|---|---|---|---|---|
| Cartesia | Not specified | Audio | $38.25 / 1M characters | — | cartesia/sonic-3-2026-01-12:cartesia |
Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max chars | 2000 |
| Formats | mp3, wav, pcm, ulaw, alaw |
Provider Notes
HTTP supports bytes and SSE; the speech WebSocket supports multiplexed context IDs. Sonic 3.5, Sonic 3, and sonic-latest support 42 languages and pronunciation dictionaries. Sonic 3 supports speed, volume, and emotion; Cartesia currently disables speed and volume on Sonic 3.5/latest while retaining emotion. Sonic 2 and Turbo use their reduced language sets and reject generation_config. sonic-latest is mutable, exact-only, and unsuitable for production pinning.
Performance
Status
Current catalog availability. Your workspace’s access is checked separately before a request runs.
A live availability check is not available right now.
Getting Started
Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.
curl "$AUDIOLAB_API_URL/v1/audio/speech" \
-H "Authorization: Bearer $AUDIOLAB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "cartesia/sonic-3-2026-01-12",
"input": "Make every word count.",
"voice": "auto",
"response_format": "mp3"
}' --output speech.mp3Request Parameters
Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.
| Parameter | Details |
|---|---|
model | cartesia/sonic-3-2026-01-12 — Required model identifier. |
transport | View Accepted Values |
output_format | View Accepted Values |
language | View Accepted Values |
context_id | View Accepted Values |
add_timestamps | View Accepted Values |
add_phoneme_timestamps | View Accepted Values |
use_normalized_timestamps | View Accepted Values |
pronunciation_dict_id | View Accepted Values |
generation_config | View Accepted Values |
continue (WebSocket) | View Accepted Values |
max_buffer_delay_ms (WebSocket) | View Accepted Values |
flush (WebSocket) | View Accepted Values |
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max chars | 2000 |
| Formats | mp3, wav, pcm, ulaw, alaw |
Similar Models
Explore more text-to-speech and compare their capabilities.
| Model | Context | Input Price | Output Price |
|---|---|---|---|
| Sonic 3.6Cartesia | Not specified | $38.25 / 1M characters | — |
| Sonic 3.6 (2026-08-27)Cartesia | Not specified | $38.25 / 1M characters | — |
| Sonic 3.5Cartesia | Not specified | $38.25 / 1M characters | — |
| Sonic 3.5 (2026-05-04)Cartesia | Not specified | $38.25 / 1M characters | — |
| Sonic 3Cartesia | Not specified | $38.25 / 1M characters | — |
| Sonic LatestCartesia | Not specified | $38.25 / 1M characters | — |