{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2026-08-27-cartesia-sonic-3-6/","md":"https://postcutoff.com/e/2026-08-27-cartesia-sonic-3-6/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-08-27-cartesia-sonic-3-6","date":"2026-08-27","date_precision":"day","short_title":"Cartesia Sonic-3.6 goes GA and tops the Artificial Analysis Speech Arena","deck":null,"takeaway":"Cartesia made Sonic-3.6 generally available on 2026-08-27 (beta 2026-08-17), three months after Sonic-3.5.","category":"model-release","category_label":"Model releases","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Cartesia: Introducing Sonic-3.6","url":"https://www.cartesia.ai/blog/sonic-3.6","type":"official","group":"primary","domain":"cartesia.ai"},{"n":2,"title":"Cartesia docs: Sonic 3.6","url":"https://docs.cartesia.ai/build-with-cartesia/tts-models/latest","type":"docs","group":"primary","domain":"docs.cartesia.ai"},{"n":3,"title":"Cartesia: Introducing Ink-2","url":"https://www.cartesia.ai/blog/introducing-ink-2","type":"official","group":"primary","domain":"cartesia.ai"},{"n":4,"title":"Artificial Analysis TTS leaderboard","url":"https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice","type":"official","group":"primary","domain":"artificialanalysis.ai"}],"official":4,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Cartesia"],"title":"Cartesia Sonic-3.6 goes GA and tops the Artificial Analysis Speech Arena","summary":"Cartesia made Sonic-3.6 generally available on 2026-08-27 (beta 2026-08-17), three months after Sonic-3.5. The state-space-model TTS replies in under 90 ms, supports 44 languages (adding Odia and Urdu) and was preferred over Sonic-3.5 in up to 93% of blind tests. In September it ranked #1 on the Artificial Analysis Speech Arena (~1279 Elo) until ElevenLabs' Eleven v4 took the top spot on 2026-09-28. Cartesia also shipped the Ink-2 streaming STT (2026-07-09) with built-in turn detection.","key_facts":["API id sonic-3.6 (snapshot sonic-3.6-2026-08-27); backwards compatible with sonic-3.5","<90 ms reply; ~132 chars/s generation (~2x Sonic 3 Conversational); 99.9% uptime SLA","44 languages with instant voice cloning; locale-aware numbers/dates","Artificial Analysis: #1 at ~1279 Elo (25 Sept 2026), #2 (1275) behind Eleven v4 on 29 Sept","sonic-2, sonic-turbo and sonic-3 snapshots sunset 2026-10-20"],"key_numbers":[],"tags":["tts","speech","voice-agents","state-space-models","voice"],"science":null,"body_md":"## What happened\n\nCartesia updated its Sonic TTS again: Sonic-3.5 in May, Sonic-3.6 in August. The update focused on naturalness, accent retention and faithful reading of structured content.\n\n## Why it matters\n\nVoice-agent TTS competition moved fast in Aug-Sept 2026. Cartesia, Inworld (TTS-2), Google (Gemini 3.8 Flash TTS), Alibaba and ElevenLabs (v4) swapped the Artificial Analysis #1 spot within weeks. Cartesia's SSM architecture is the main non-transformer contender at the frontier.","disputed":[],"related":[{"id":"2026-09-28-elevenlabs-eleven-v4","url":"https://postcutoff.com/e/2026-09-28-elevenlabs-eleven-v4/","date":"2026-09-28","date_precision":"day","short_title":"ElevenLabs launches Eleven v4 and Eleven v4 Turbo, #1 on Artificial Analysis TTS arena","deck":null,"takeaway":null,"category":"model-release","category_label":"Model releases","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":11,"official":7,"filed":"2026-09-29","updated":"2026-09-29","orgs":["ElevenLabs"]},{"id":"2026-09-15-gemini-3-8-live-and-tts","url":"https://postcutoff.com/e/2026-09-15-gemini-3-8-live-and-tts/","date":"2026-09-15","date_precision":"day","short_title":"Google ships Gemini 3.8 Live voice models and Gemini 3.8 Flash TTS with voice design and cloning","deck":null,"takeaway":"Completes a full voice stack (transcription, reasoning, real-time dialogue, speech synthesis, cloning) on one API; voice cloning also raises misuse concerns.","category":"product","category_label":"Products","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":12,"official":10,"filed":"2026-09-29","updated":"2026-09-30","orgs":["Google"]},{"id":"2026-08-31-inworld-realtime-tts-2","url":"https://postcutoff.com/e/2026-08-31-inworld-realtime-tts-2/","date":"2026-08-31","date_precision":"day","short_title":"Inworld Realtime TTS-2 reaches GA with audio-aware, prompt-directed speech","deck":null,"takeaway":"TTS-2 closes the loop between listening and speaking in a cascaded voice stack: the TTS hears the user, not just the transcript.","category":"model-release","category_label":"Model releases","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":5,"official":3,"filed":"2026-09-29","updated":"2026-10-03","orgs":["Inworld AI"]}],"people":[],"posts":[],"videos":[],"models":[{"id":"cartesia-sonic-3-6","name":"Cartesia Sonic-3.6","url":"https://postcutoff.com/m/cartesia-sonic-3-6/"}],"changes":[{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-09-29","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":119,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":58,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":149,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":88,"in_training_data":false}],"short_url":null}