Cartesia's current flagship text-to-speech model; this alias tracks the newest stable Sonic 3.6 snapshot. It covers 44 languages, adding Odia and Urdu, reads Latin-script Hindi (Hinglish), and is backwards compatible with Sonic 3.5.
Pinned Sonic 3.6 snapshot released August 27, 2026 and currently the build behind the sonic-3.6 alias. Unlike the alias it never changes, which Cartesia recommends for production traffic needing consistent output.
Streaming speech-to-text flagship from Cartesia, released May 22, 2026, with built-in turn detection that emits start, eager-end, resume and end events without a separate VAD. Since September 17, 2026 it transcribes English, French, Hindi, Japanese and Spanish.
Previous-generation Sonic model, superseded by Sonic 3.6 in August 2026 but still served as a stable option. Covering 42 languages, it improved on Sonic 3 in alphanumeric read-out, English heteronyms and multilingual pronunciation; the alias does not auto-upgrade to 3.6.
Only dated snapshot of Sonic 3.5, released May 4, 2026 and pinned behind the sonic-3.5 alias. It remains stable with no announced sunset; its successor is sonic-3.6-2026-08-27.
Second Sonic 3 snapshot, promoted to stable on January 12, 2026 with more consistent speed and volume, stronger adherence to custom IPA pronunciations, and better Hindi and Korean prosody. It is the current sonic-3 target and remains supported.
Third-generation Sonic model launched October 27, 2025, now two releases behind Sonic 3.6. Supports 42 languages, [laughter] tags, and speed, volume and emotion controls; the alias resolves to the stable sonic-3-2026-01-12 snapshot.
Launched June 10, 2025, Ink-Whisper was Cartesia's first speech-to-text model: a streaming-tuned variant of OpenAI's Whisper (large-v3-turbo baseline) with dynamic chunking. Now an older model behind Ink 2, it covers about 100 languages and alone handles batch transcription.
Deprecated mutable alias that served as Cartesia's non-snapshotted beta track around the Sonic 3.5 release in mid-2026. Cartesia now directs users to sonic-preview instead and documents no current target, so it is unsuitable for pinning.
Beta TTS track for testing upcoming Cartesia model and API changes; it updates without notice and is not meant for production. It took over from the deprecated sonic-latest and sonic-3-latest aliases in mid-2026.
