Cartesia Sonic-3.6
Speech and audio
sonic-3.6
$0.037 per 1K characters
Cartesia’s streaming speech-to-text built for voice agents; pairs with Sonic-3.6.
Model idink-2
PricePrice not published
Checked29 September 2026
44newer speech and audio models since its release
The 5 newest are listed. All speech and audio models
2 ways to use Cartesia Ink-2 (streaming STT), with the model id each provider expects.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Cartesia API | ink-2 |
wss://api.cartesia.ai/stt/websocket?model=ink-2 |
docs.cartesia.ai |
| Cartesia API (beta) | ink-preview |
wss://api.cartesia.ai/stt/websocket |
Price not published.
No price source linked. Checked 29 September 2026.
What its maker marketed at launch, and what people found later, each with its source.
Emits turn.start / turn.update / turn.eager_end / turn.resume / turn.end events so agents need no separate VAD; 89% precision, 93% F1 on endpointing; ~0.1 s time-to-final-transcript.
3.4% WER on AA-AgentTalk, ranked #1 on Artificial Analysis’s streaming STT leaderboard (company claim, July 2026).
Found after launch
Keyterm prompting and configurable turn detection added 2026-08-11.
Launched English-only (blog 2026-07-09); the current stable ink-2 snapshot is dated 2026-09-17 and supports English, French, Hindi, Japanese, Spanish. Query params: model, encoding, sample_rate, cartesia_version=2026-08-14; send finalize when user stops. Older model: ink-whisper (1 credit/s streaming). Ink-2 credit price not found on pricing page (plans list included STT hours).
Sources: https://docs.cartesia.ai/build-with-cartesia/stt/latest , https://docs.cartesia.ai/api-reference/stt/stt , https://www.cartesia.ai/blog/introducing-ink-2
Not yet checked against an official source: Some press dates an earlier Ink 2 release to May 2026 (unverified).