diarization

NVIDIA released Nemotron 3.5 Transcribe, an open-weight promptable model for multilingual transcription, speaker diarization, translation, and audio Q&A with top leaderboard results, alongside the Granary v2 data pipeline and NeMo fine-tuning recipes for domain adaptation.

Maybloc launches as a new state-of-the-art speech-to-text product for multi-speaker audio, claiming the lowest diarization error across several benchmarks, supporting 45 languages and up to 25 speakers, with add-ons like subtitles, PII redaction, summaries, and translation.

This paper introduces SI-cpWER, a corpus-level metric for persistent speaker attribution across meetings, and evaluates 5 commercial diarized-STT APIs plus 2 open baselines (and their own ThyVoice system) on NOTSOFAR and CHiME-6, showing that per-meeting ranking doesn't reflect cross-meeting identity consistency. A short version was accepted at IEEE SLT 2026 Demo Track.

The paper introduces target-speaker unlearning ASR (TSU-ASR) and proposes a novel Enrollment-Conditioned Gating module for dynamic opt-out of speakers during inference in LLM-based ASR, enhancing privacy in online conferencing.

VoiceArena launched Diarization Bench, a benchmark comparing 12 diarization systems on real-world audio, highlighting how accuracy drops with overlap and the impact of collar effect on error rates.

The article describes a user's hands-on experience with the Nemotron 3 Diarization model, highlighting its streaming capabilities and integration into a speech-to-speech setup with a robot.

VibeVoice-ASR-Streaming is an LLM-based end-to-end model for streaming speaker-attributed speech recognition, achieving state-of-the-art performance with released 1.5B and 7B model weights.

Meta introduces Muse Voice Transcribe, a real-time audio perception model that excels in streaming ASR and diarization with multilingual support, topping public benchmarks.

MOSS-Transcribe-Diarize, an open-source ASR model with multi-speaker diarization and hotword biasing, trends on Hugging Face after release.

MOSS-Transcribe-Diarize-0.9B is an open-source end-to-end audio understanding model for long-form multi-speaker transcription, diarization, and timestamp generation, released by Mosi AI under Apache 2.0.

Universal-3.5 Pro improves native code switching, diarization, and adds more languages, enhancing speech recognition capabilities.

WhisperX is a tool for fast automatic speech recognition with word-level timestamps and speaker diarization, offering 70x realtime transcription using Whisper large-v2.

Fine-tuned Cohere Transcribe, the best open-source speech-to-text model, to support diarization and timestamps. The new model is available on Hugging Face.

PrivateScribe.ai is a fully local, MIT-licensed AI transcription platform with HIPAA safeguards, now featuring a bundled macOS app, onboarding wizard, speaker diarization, and encryption.