C
Cartesia Sonic 3.6
Cartesia Sonic 3.6, a text-to-speech model from Cartesia.
speechModelOverride: { model: "cartesia-sonic-3.6" }
CCartesia·Released August 2026
Pricing
- List price
- ~$37 / 1M characters
- Per 1M characters
- $37.38
Specifications
- Context window
- 5,000 tokens
- Released
- August 2026
- Model string
- sonic-3.6
- Capabilities
- RealtimeLow latency
Parameters
Model options, passed in
speechModelOverride.config.| Parameter | Type | Default | Range / options |
|---|---|---|---|
voiceA Cartesia voice. Any voice id from https://play.cartesia.ai/voices, including the account's own, can be pasted in. | Select | db6b0ed5-d5d3-463d-ae85-518a07d3c2b4 | db6b0ed5-d5d3-463d-ae85-518a07d3c2b447c38ca4-5f35-497b-b1a3-415245fb35e1a33f7a4c-100f-41cf-a1fd-5822e8fc253ff786b574-daa5-4673-aa0c-cbe3e8534c02a5136bf9-224c-4d76-b823-52bd5efcffcc5ee9feff-1265-424a-9d7f-8e4d431a12c7+12 |
languageThe language the text is in. Unset, Cartesia takes the voice's own. Sonic speaks 44 languages; any of their codes can be pasted in. | Select | — | enesfrdeitpt+10 |
emotionThe feeling the voice carries. In the text itself, <emotion value="excited"/> changes it mid-way and [laughter] laughs. | Select | — | neutralcalmcontenthappyexcitedenthusiastic+32 |
speedSpeaking speed. 1.0 is normal. | Number | 1 | 0.6–1.5, step 0.05 |
volumeLoudness. 1.0 is normal. | Number | 1 | 0.5–2, step 0.05 |
format | Select | mp3 | mp3wav |
Voices · 18
Previews aren’t available for this model’s voices.
Use this model
await mindstudio.textToSpeech({ text: "...", speechModelOverride: { model: "cartesia-sonic-3.6", config: { voice: "db6b0ed5-d5d3-463d-ae85-518a07d3c2b4", language: "en", }, }, });