#speech-to-text · AI & ML

Speech-to-text

Speech recognition, transcription and dictation, from open models to local apps.

This week (Oct 27 – Nov 2), the top-ranked are hex (+3,169), VoiceStudio (+10,112) and AudioSmith (+125). The 105 ranked repos gained 24,126 stars, 12% more than the week before.

Updated Nov 2, 10:36 UTC · ranked every hour from GitHub’s daily star counts

Updated 35 min ago

GitHub topic ↗

Emerging this week

Showing 7 of 7

How Upstar ranks

Listed by acceleration against their usual week; the score is the rankings’ own: stars gained in 7 days ÷ √(stars before, minimum 100).

1
anomalyco/hex Local voice dictation for mac, windows and linux 74× its usual pace (~43 a week) Rust Rust · 3.8k total Healthy Spotted at 501 stars
Gained in 7 d +3.2k Score 129.5 Total 3.8k
2
google-gemini/jot-gemini-transcribe-macOS Gemini 3.5 Transcribe demo. Hold a key. Speak. It types. Smart dictation for macOS. 7× its usual pace (~8 a week) Swift Swift · 554 total Mixed signals
Gained in 7 d +58 Score 2.6 Total 554
3
bayshier/voicestudio-zh VoiceStudio 中文版：开源、完全本地的 ElevenLabs 替代品——语音克隆、语音设计、视频配音、听写、转写与有声书，646 种语言（译自 debpalash/VoiceStudio，AGPL-3.0） 5× its usual pace (~12 a week) Python Python · 195 total
Gained in 7 d +58 Score 5.0 Total 195
4
wassgha/rescript 🎬 Open source, transcript-based video/audio editor that lives in the browser. 5× its usual pace (~15 a week) TypeScript TypeScript · 1k total Mixed signals
Gained in 7 d +68 Score 2.2 Total 1k
5
sunerpy/voltip Push-to-talk voice typing for Windows, macOS, Linux and Android. On-device or cloud speech recognition, AI polish with presets, a dictionary, rules and scenes, long recordings with subtitles; the phone works on its own or pairs end-to-end encrypted as the computer's microphone and keyboard. After quiet weeks Rust Rust · 79 total
Gained in 7 d +42 Score 4.2 Total 79
6
fermionresearch/phonon Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images 2× its usual pace (~15 a week) Python Python · 324 total
Gained in 7 d +33 Score 1.9 Total 324
7
nyosegawa/speech.cpp Speech synthesis, speech recognition and voice activity detection for voice conversation, in C++ on ggml: Qwen3-TTS, Irodori-TTS, Qwen3-ASR, ReazonSpeech, parakeet and Silero VAD on Metal, Vulkan and the CPU, with an OpenAI-compatible server and live transcription. 2× its usual pace (~51 a week) C++ C++ · 317 total
Gained in 7 d +107 Score 7.4 Total 317

Back to the ranking Past weeks: Oct 26 Oct 19