Speaker Diarization Python Packages

funasr

Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

whisper-timestamped

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

espnet

End-to-End Speech Processing Toolkit

vezir

Self-hosted scribe service for team meetings. Record on any laptop (TUI / GUI / CLI), transcribe + diarize + summarize on your own GPU server, label speakers via shared web UI. Optional confidential TEE summarization. Over nvpn or Tailscale.

funasr-onnx

Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

diart

A python package to build AI-powered real-time audio applications

spectralcluster

Python re-implementation of the (constrained) spectral clustering algorithms used in Google's speaker diarization papers.

wespeakerruntime

Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit

ffvoice

Offline speech-to-text & speaker diarization for AI agents — Whisper ASR + MCP server + CLI + Python bindings, fully on-device, no cloud | 离线语音识别与说话人分离,Agent 开箱即用

diarize

Speaker diarization for Python — "who spoke when?" CPU-only, no API keys, Apache 2.0. ~10.8% DER on VoxConverse, 8x faster than real-time.

whisper-run

Faster Whisper with Speaker Diarization

polyvoice

Speaker diarization for Rust — who spoke when. ONNX-powered: Silero VAD, WeSpeaker embeddings, Pyannote segmentation, K-means/AHC clustering, overlap detection. Python bindings & CLI included.

speechlib

Speechlib is a library that unifies speaker diarization, transcription and speaker recognition in a single pipeline to create transcripts for audio conversations with actual speaker names and time tags. This library also contains audio preprocessor functions.

coro-asr

OpenAI-compatible ASR + speaker-diarization HTTP server with pluggable backends (Faster-Whisper, onnx-asr Parakeet, onnx-genai Nemotron) and NeMo Sortformer diarization.

funasr-torch

Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

sonata-asr

SONATA (SOund and Narrative Advanced Transcription Assistant): An advanced ASR system that captures human expressions including emotive sounds and non-verbal cues.

senko

Very fast, accurate speaker diarization

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.

funasr-python

Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

precisetranscribe

Utilities for transcribing audio files using the Whisper API.

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.

diarizationlm

This repository contains audio samples and supplementary materials accompanying publications by the "Speaker, Voice and Language" team at Google.

voxkitchen

Declarative speech data processing toolkit — write a YAML recipe, run vkit run, get training-ready data. Ships a Claude Code skill.

qwen-aligner-toolkit

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