1.jamiepine / voicebox
The open-source AI voice studio. Clone, dictate, create.
+3,097 stars
from 56,113 · score 8.04
Trending repositories
Ranked by Attention Score: stars gained over the last 30 complete days
11 repositories by Attention Score · Oct 4, 2026 – Nov 2, 2026 (UTC)
2.kajisho5 / ffmpeg-skill
Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.
+3,023 stars
from 1,261 · score 8.01
3.SYSTRAN / faster-whisper
Faster Whisper transcription with CTranslate2
+724 stars
from 25,650 · score 6.59
4.m-bain / whisperX
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
+672 stars
from 24,324 · score 6.51
5.chidiwilliams / buzz
Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.
+588 stars
from 21,755 · score 6.38
6.abus-aikorea / voice-pro
Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.
+469 stars
from 12,921 · score 6.15
7.QuentinFuxa / WhisperLiveKit
Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.
+112 stars
from 11,088 · score 4.73
8.goodroot / hyprwhspr
Native speech-to-text for Linux - Fast, accurate, private, and hackable system-wide dictation
+45 stars
from 1,223 · score 3.83
9.PaddlePaddle / PaddleSpeech
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
+18 stars
from 12,683 · score 2.94
10.linto-ai / whisper-timestamped
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
+6 stars
from 2,851 · score 1.95
11.rcspam / dictee
Push-to-talk voice dictation for Linux. 100% local, multilingual (25+ languages), with speaker diarization. Qt frontend, Rust backend on NVIDIA Parakeet via ONNX Runtime. KDE Plasmoid integrated.
+3 stars
from 65 · score 1.39