Cartesia Sonic
Sub-100ms time-to-first-byte — built for realtime voice agents.
Intelligence index
—
Composite of MMLU, GPQA, MATH & HumanEval
Speed
—
Median across providers, steady state
Price per 1k characters
$0.065
At a glance
- Time to first token
- 0.09s
- Input modalities
- text
- Output modalities
- audio
- License
- Proprietary
- Provider
- Cartesia
Strengths
- Fastest TTFB on the market
- Voice cloning
Weaknesses
- Newer ecosystem
Best for
- Realtime voice agents
- Live conversations
Models you should also evaluate
Cartesia Sonic vs… popular head-to-heads
One-click matchups against the models people compare Cartesia Sonic with most.
Cartesia Sonic — frequently asked questions
Cartesia Sonic is a text-to-speech model from Cartesia, released on 29 May 2024. Sub-100ms time-to-first-byte — built for realtime voice agents.
Need help choosing between models?
Compare every option in one sortable table — intelligence, speed and price on a single page.