{"id":"assemblyai-stt-3-7-realtime-agent","slug":"assemblyai-stt-3-7-realtime-agent","name":"AssemblyAI-STT-3.7-Realtime-Agent","orgId":"assemblyai","family":"assemblyai-stt-3-7-realtime-agent","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-Agent","assemblyai-stt-3-7-realtime-agent","assemblyai stt 3.7 realtime agent","assemblyai stt-3.7-realtime-agent","assemblyai-stt-3.7-realtime-agent"],"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 voice agents. Official docs describe 32 languages in one stream with automatic detection, plus keyterm prompting, context carryover, conversation memory, and Voice Focus. It replaces Universal-3.6 Pro Realtime for voice-agent use. Live on AssemblyAI's Realtime Speech-to-Text API as speech_model=\"assemblyai-stt-3-7-realtime-agent\" at $0.45 per hour of session time. 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-agent","openWeights":"no","facts":[{"label":"Task","value":"Streaming speech-to-text for voice agents, including multilingual agents with native code switching and agents in noisy environments"},{"label":"Languages","value":"32 languages in one stream, with automatic detection and native code switching (official introducing post, models reference, and which-model guide)"},{"label":"API","value":"Realtime Speech-to-Text API: WebSocket wss://streaming.assemblyai.com/v3/ws with speech_model=\"assemblyai-stt-3-7-realtime-agent\" and an API key. Official introducing post: the endpoint and message protocol are unchanged from Universal-3.6 Pro Realtime"},{"label":"Pricing","value":"$0.45 per hour of session time, the same rate AssemblyAI states for Universal-3.6 Pro Realtime (official pricing reference and Realtime-Agent research post). Official Voice Focus docs: Voice Focus is available on this model as near-field or far-field, at +$0.10/hr"},{"label":"Features","value":"Official streaming docs: built-in keyterm prompting, context carryover, and conversation memory, and Voice Focus (near-field or far-field). Official research post: the model receives text context and acoustic context from earlier in the call; it is trained on real voice-agent and telephony conversations with speaker and role labels"},{"label":"Availability","value":"Generally available on AssemblyAI's self-serve Realtime Speech-to-Text API. Official changelog dated 2026-11-18. Official docs list it as the replacement for Universal-3.6 Pro Realtime in voice-agent use"},{"label":"Related","value":"Separate from AssemblyAI-STT-3.7 (pre-recorded) and from AssemblyAI-STT-3.7-Realtime (live conversations and notetakers), from AssemblyAI-TTS-1, and from Universal-3.5 Pro"},{"label":"Weights","value":"Not released"}],"claims":["Lab claim: on 12,460 English voice-agent calls, AssemblyAI reports a lower word error rate and a lower entity error rate than the other 25 streaming models it ran, including Soniox Realtime v6, ElevenLabs Scribe v3 Live, and Deepgram Nova-3 (self-reported, official Realtime-Agent research post).","Lab claim: it returns the final transcript 86 ms after the caller stops speaking, half the 172 ms AssemblyAI measured for Universal-3.6 Pro Realtime on the same day (self-reported, official research post).","Lab claim: versus Universal-3.6 Pro Realtime, end-of-turn F1 rose from 83.60% to 85.52%, precision from 76.08% to 78.97%, and false end-of-turn events fell from 23.92% to 21.03% (self-reported, official research 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":"AssemblyAI-STT-3.7-Realtime-Agent research post","url":"https://www.assemblyai.com/blog/assemblyai-stt-3-7-realtime-agent-research","date":"2026-11-18"},{"kind":"lab","title":"Streaming model selection","url":"https://www.assemblyai.com/docs/streaming/select-the-speech-model"},{"kind":"lab","title":"Voice Focus","url":"https://www.assemblyai.com/docs/streaming/voice-focus"},{"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-Agent 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":[]}