Topic
Technology for converting spoken audio into text, including speech recognition models, accuracy metrics, speaker diarization and transcript formatting.
Microsoft's official plugin lets LiveKit Agents stream live audio to MAI-Transcribe-2-Streaming, a realtime model covering roughly 60 languages. The service is still a public preview that Microsoft does not recommend for production.
Reality
Preterview's developer cut mid-answer interruptions from 22% to 3.1% by confirming Deepgram's 300ms silence cutoff with a completeness check. The fix added 140ms at the median, against about 900ms for a longer timer, and threw away one drafted reply in five.
Reality
SpaceXAI's new transcription model costs the same as the one it replaces and drops into existing code, so the migration work is re-validating accuracy claims that rest mostly on the company's own test sets.
Reality
Loquent's 14,000 vox-bench runs found Claude Haiku's latency tail at 2.85x its median while ElevenLabs tightened to 1.92x. Alert thresholds tuned to June's data would now be watching the wrong stage of the pipeline.
Reality
Nabeel Baghoor shipped a lecture note-taker before he shipped voice agents, and reports that his accuracy wins on the note-taking side came from the recording path and a domain vocabulary bias list, with provider benchmarks a distant third.
Reality
The published floor is six months for generally available models, three for Codex and chat variants, and as little as two weeks for anything with preview in the name. The dated entries in the log sit on the floor.
Reality