{"id":"assemblyai-stt-3-7-realtime","slug":"assemblyai-stt-3-7-realtime","name":"AssemblyAI-STT-3.7-Realtime","orgId":"assemblyai","family":"assemblyai-stt-3-7-realtime","releaseDate":null,"availability":"ga","openWeights":false,"license":null,"paramsTotal":null,"paramsSource":null,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://www.assemblyai.com/llms/models.md","hfRepo":null,"modalities":["audio"],"aliases":["AssemblyAI-STT-3.7-Realtime","assemblyai-stt-3-7-realtime","assemblyai stt 3.7 realtime","assemblyai stt-3.7-realtime","assemblyai-stt-3.7-realtime"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-11-18","announced":"2026-11-17","blurb":"AssemblyAI's streaming speech-to-text model in the AssemblyAI-STT-3.7 family, built for live conversations that end in a transcript: meetings, calls, captions, and notetakers. Official docs describe 32 languages in one stream with automatic detection, and speaker labels that are final the moment a turn ends, with no revision pass. It replaces Universal-Streaming and Universal-Streaming Multilingual. Live on AssemblyAI's Realtime Speech-to-Text API as speech_model=\"assemblyai-stt-3-7-realtime\" at $0.30 per hour of session time. Official docs say it is not tuned for agent turn-taking. No weights. Official models.md dates the family launch to November 17, 2026; the changelog and lab blogs are dated November 18.","api":"live","apiModelId":"assemblyai-stt-3-7-realtime","openWeights":"no","facts":[{"label":"Task","value":"Streaming speech-to-text for live conversations: meetings, calls, captions, notetakers, and agent assist. Official docs: not tuned for agent turn-taking"},{"label":"Languages","value":"32 languages in one stream, with automatic language detection (official introducing post, models reference, and changelog)"},{"label":"API","value":"Realtime Speech-to-Text API: WebSocket wss://streaming.assemblyai.com/v3/ws with speech_model=\"assemblyai-stt-3-7-realtime\" and an API key. Official introducing post: the endpoint and message protocol are unchanged from the previous streaming models; speaker labels no longer send a SpeakerRevision message"},{"label":"Pricing","value":"$0.30 per hour of session time (official pricing reference and introducing post). Official Voice Focus docs: Voice Focus is not available on this model"},{"label":"Speaker labels","value":"Official introducing post: from the start of a new session, speaker labels are final the moment a turn ends and are nearly as accurate as labels from pre-recorded audio; there is no revision pass. Partials arrive about once a second"},{"label":"Availability","value":"Generally available on AssemblyAI's self-serve Realtime Speech-to-Text API. Official changelog dated 2026-11-18. It replaces Universal-Streaming and Universal-Streaming Multilingual, which official docs mark deprecated as of November 17, 2026 (tentative retirement February 1, 2027)"},{"label":"Related","value":"Separate from AssemblyAI-STT-3.7 (pre-recorded) and from AssemblyAI-STT-3.7-Realtime-Agent (voice agents), from AssemblyAI-TTS-1, and from Universal-3.5 Pro"},{"label":"Weights","value":"Not released"}],"claims":["Lab claim: measured on the same recordings, AssemblyAI reports a lower live diarization error rate than the other realtime providers it measured on CallHome (40 unscripted telephone calls) and on NOTSOFAR (129 real meetings recorded on a single distant microphone, up to seven speakers), including ElevenLabs Scribe v3 Live and Meta Muse Voice Transcribe (self-reported, official introducing post)."],"sources":[{"kind":"lab","title":"AssemblyAI models reference (llms/models.md)","url":"https://www.assemblyai.com/llms/models.md","date":"2026-11-17"},{"kind":"lab","title":"Speech model versions and deprecations","url":"https://www.assemblyai.com/docs/getting-started/model-versions-and-deprecations","date":"2026-11-17"},{"kind":"lab","title":"AssemblyAI changelog: AssemblyAI-STT-3.7","url":"https://www.assemblyai.com/changelog/","date":"2026-11-18"},{"kind":"lab","title":"Introducing AssemblyAI-STT-3.7 (AssemblyAI blog)","url":"https://www.assemblyai.com/blog/introducing-assemblyai-stt-3-7","date":"2026-11-18"},{"kind":"lab","title":"Streaming model selection","url":"https://www.assemblyai.com/docs/streaming/select-the-speech-model"},{"kind":"lab","title":"AssemblyAI pricing reference","url":"https://www.assemblyai.com/pricing.md"},{"kind":"lab","title":"AssemblyAI on X: AssemblyAI-STT-3.7","url":"https://x.com/AssemblyAI/status/2123080177508929849","date":"2026-11-18"}],"firstBenchmark":null},"organization":{"id":"assemblyai","name":"AssemblyAI","slug":"assemblyai","country":null,"url":"https://www.assemblyai.com","color":"#A39E8F","mark":"AS"},"price":null,"answer":{"word":"Pending benchmarks.","scope":"Announced Nov 17, 2026; no independent results yet.","lead":"As of Nov 22, 2026, AssemblyAI-STT-3.7-Realtime is pending benchmarks on isitsota: announced Nov 17, 2026, with no independent results on the boards we track yet.","confidence":"low"},"status":"PENDING_BENCHMARKS","verdicts":[]}