Pyannote Python Packages

polyvoice

CPU speaker diarization with native INT8 kernels. Rust, CLI, Python and C interfaces; no ONNX Runtime in the core.

senko

Very fast, accurate speaker diarization

dharma-transcribe

Headless multilingual transcription pipeline for Buddhist dharma teachings (Tibetan, Sanskrit, English, Japanese)

polyphon-ai

Local, identity-aware speech transcription and diarization engine — turns multi-speaker audio into structured, named intelligence, 100% offline.

whisper-run

Faster Whisper with Speaker Diarization

whosaid

Local Whisper transcription + speaker diarization for Apple Silicon — who said what, fully offline and on-device

transcribe-critic

Multi-source transcript merging inspired by textual criticism — LLM adjudicates multiple Whisper, YouTube captions & external transcripts for higher quality. Includes speaker diarization and summarization.

whisper-smith

CLI and Python library for transcribing audio with OpenAI Whisper — supports txt, json, srt, vtt output and optional speaker diarization.

gryannote

Provide Gradio custom components to make the diarization-based audio labeling process easier and faster.

qwen-aligner-toolkit

Production toolkit around Qwen3-ForcedAligner: multilingual word-level alignment, VAD, and speaker diarization.

taiwan-asr-toolkit

Production-grade Traditional Chinese / Taiwan Mandarin speech-to-text. Qwen3-ASR + MediaTek Breeze-ASR-25, hot-word injection, LLM polish, speaker diarization. RTF up to 1554x on RTX 5090, 56 TDD tests.

voicetag

Speaker identification powered by pyannote and resemblyzer

voxsolo

Isolate one speaker from any recording — speaker diarization + verbatim voice isolation CLI. Silences overlaps, proves bit-identical audio, exports EDL/SRT/markers for Resolve, Premiere, Audacity.

rtrimmer

Python package to trim RTTM diarization files and optionally audio files to a user-specified time range.

transcript-critic

Multi-source transcript merging inspired by textual criticism — LLM adjudicates multiple Whisper, YouTube captions & external transcripts for higher quality. Includes speaker diarization and summarization.