Voice Transcription Enhancements

This cluster focuses on adding and improving voice transcription features across various platforms, particularly emphasizing support for new audio transcription providers.

17 PRs

feat macos stt voice-call

#	Title	Author	Created	GitHub
5656	fix(macos): prevent crash on launch when no microphone available	sfo2001	2026-01-31	View
8848	feat(stt): Add Whisper as first-class audio transcription provider	emadomedher	2026-02-04	View
9703	feat(macos): Voice settings restructure + Whisper transcription support	nsd97	2026-02-05	View
10012	Webui voice	nanxiacc	2026-02-06	View
11334	feat: add Mistral/Voxtral audio transcription provider	JamesEBall	2026-02-07	View
11965	feat(ui): add speech-to-text dictation to web chat via Deepgram Flux	billgetman	2026-02-08	View
12157	feat(macos): add Granola-style meeting notes with live transcription	npow	2026-02-08	View
12597	voice-call: add Asterisk ARI provider + core STT	w0s1nsk1	2026-02-09	View
14208	feat(media): add AssemblyAI audio transcription provider	jmoraispk	2026-02-11	View
14458	fix(voicewake): avoid crash on foreign transcript ranges	guchang	2026-02-12	View
14730	Add Mistral AI as a model provider	jaimegh-es	2026-02-12	View
14934	fix: add mistral to MemorySearchSchema provider/fallback unions	ThomsenDrake	2026-02-12	View
16258	feat(models): add Mistral AI provider support	joeVenner	2026-02-14	View
18235	macOS: prevent Voice Wake crash when no input device is available	agisilaos	2026-02-16	View
19427	feat: add Soniox speech-to-text provider	matjaz	2026-02-17	View
20530	feat: add Astrai as implicit provider (intelligent inference router)	beee003	2026-02-19	View
22402	Add runtime.stt.transcribeAudioFile for plugin STT access	benthecarman	2026-02-21	View