Faster Whisper Python Packages

stream-translator-gpt

A stream-translator fork with VAD based audio slicing & GPT / Gemini translation.

voicepad

Command-line interface for voice recording and GPU-accelerated transcription.

voicepad-core

Core audio processing for Voicepad.

tafrigh

تفريغ النصوص وإنشاء ملفات SRT و VTT باستخدام نماذج Whisper وتقنية wit.ai.

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.

edgevox

Offline voice agent framework for robots.

openlrc

Transcribe (whisper) and translate (gpt) voice into LRC file.

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.

voxn

A local-first memory layer for users and AI agents to capture, search, and synthesize project context.

whisper-run

Faster Whisper with Speaker Diarization

casts-down

Cross-platform CLI to download & transcribe podcasts locally — Apple Podcasts, Xiaoyuzhou, RSS feeds with built-in Whisper speech-to-text (Metal/CUDA/CPU)

whisper-autosrt

A python script COMMAND LINE utility to AUTO GENERATE SUBTITLE FILE (using faster_whisper module which is a reimplementation of OpenAI Whisper module) and TRANSLATED SUBTITLE FILE (using unofficial online Google Translate API) for any video or audio file

hns

hns is a speech-to-text CLI tool to transcribe your voice from your microphone directly to clipboard. Integrate hns with Claude Code, Ollama, LLM, and more CLI tools for powerful workflows.

whisper-streaming

Whisper realtime streaming for long speech-to-text transcription and translation

aavt

这是一个全自动（音频）视频翻译项目。利用Whisper识别声音，AI大模型翻译字幕，最后合并字幕视频，生成翻译后的视频。

bmnspeechlib

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.

stttui

Speech-to-Text TUI — offline transcription powered by faster-whisper

asrbench-cli

A command-line tool for the ASRBench framework, simplifying audio transcription system benchmarking with a single config file, supporting popular and custom transcription systems

whisper-telegram-mcp

Two-way voice for Claude via Telegram — Whisper transcription + Kokoro/OpenAI TTS as an MCP server

speech-mine

Turn audio into searchable, speaker-labeled transcripts. Built for iterative pipelines, not one-shot runs.

aavt111

这是一个全自动（音频）视频翻译项目。利用Whisper识别声音，AI大模型翻译字幕，最后合并字幕视频，生成翻译后的视频。