10 open-source GitHub repos for fully local speech-to-text, led by Whisper at 110K stars
victor_explore · x · 2026-10-19
A curated roundup of 10 open-source GitHub projects for running speech-to-text entirely on your own machine, all offline-capable (star counts as of Oct 2026):
- Whisper (110K stars, MIT): OpenAI's open-source ASR model that most of these tools build on, multilingual.
- whisper.cpp (54K stars): fast, Python-free reimplementation that runs on Mac/Windows/Linux and even iPhone.
- Handy (33K stars): free dictation app — press a key, speak, and text lands in any input field.
- Meetily (32K stars): local meeting note-taker producing transcripts and summaries, an Otter alternative.
- faster-whisper (26K stars): CTranslate2-based engine, up to 4x faster at same accuracy, with 8-bit quantization.
- WhisperX (24K stars): word-level timestamps and speaker diarization with 1% speaker labeling error.
- Buzz (22K stars): desktop app for transcribing files or mic input, with offline translation.
- Vosk (18K stars, Apache 2.0): lightweight offline toolkit supporting 20+ languages, streaming and speaker ID.
- sherpa-onnx (15K stars): one engine for phones and PCs covering recognition, synthesis, separation and verification.
- WhisperLiveKit (11K stars): self-hosted ultra-low-latency live captions with speaker labels.
More from coding & agent
- Greptile raises $50M Series B at $750M valuation, reviews 1% of all GitHub PRs — Rasmic · 2026-10-19
- Do you still review every UI change by hand when an agent writes it? — mfbzme · 2026-10-19
- Dev builds playable Tesla Roadster web game in a weekend with Opus 5.5 — edwinarbus · 2026-10-19
- Blender renders cut from 4 hours to minutes with Opus 5.5 and cloud GPUs — ravisparikh · 2026-10-19
- LangChain Hosts Life Sciences Agent Engineering Workshop: Build, Trace, Evaluate Research Agents — LangChain · 2026-10-19
- Librarian Agents: new paper lets agents curate their own long-context workspaces — charles_irl · 2026-10-19