Fermion Research's open English speech-to-text model: Parakeet-level accuracy in a 164 MB file, 174 times realtime on a MacBook Air, CC-BY-4.0.

Tencent's open-source 1.5B speech model: text to speech, voice cloning, and editing of recorded speech (words, pitch, speed, emotion, noise) from plain-language instructions.

NVIDIA's open-weight 100M-parameter model that tells who spoke when, for up to 8 speakers, live or recorded. Ranked first on VoiceArena's diarization benchmark at launch.

Microsoft's open-source frontier voice AI with TTS and ASR models.