Data / Repositories / Speech to text
Speech to text repositories on GitHub: 8 ranked by stars
8 public repositories tagged Speech to text are on GitHub, with 139,209 stars between them; 8 had a push in the last 30 days. Most are written in Python (3), Rust (2), C++ (1). The most starred: ggml-org/whisper.cpp (54,275), cjpais/Handy (33,458), screenpipe/screenpipe (21,938).
SpecStream is the live web data engine for teams and agents. It reads open-source repositories on GitHub and keeps what it reads, and this page groups that reading by topic. Ask for the repositories you track by topic, language, license or activity, and new ones and changes arrive in your sheet, CRM, Slack or agent.
Every repository, most starred first
| Repository | What it is | Language | Stars | Forks | License | Last push | Read |
|---|---|---|---|---|---|---|---|
| ggml-org/whisper.cpp | Port of OpenAI's Whisper model in C/C++ | C++ | 54,275 | 6,220 | MIT | Oct 6 | Oct 11 |
| cjpais/Handy | A free, open source, and extensible speech-to-text application that works completely offline. | Rust | 33,458 | 3,115 | MIT | Oct 10 | Oct 11 |
| screenpipe/screenpipe | YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context | Rust | 21,938 | 2,243 | Oct 14 | Oct 14 | |
| QuentinFuxa/WhisperLiveKit | Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs. | Python | 11,141 | 1,147 | Apache-2.0 | Oct 1 | Oct 14 |
| OpenWhispr/openwhispr | Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform. | JavaScript | 9,416 | 1,176 | MIT | Oct 14 | Oct 14 |
| dograh-hq/dograh | Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and… | Python | 5,868 | 1,493 | BSD-2-Clause | Oct 14 | Oct 14 |
| FluidInference/FluidAudio | Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source. | Swift | 3,012 | 466 | Apache-2.0 | Oct 9 | Oct 11 |
| 100yenadmin/fish-audio-hermes | Official Fish Audio plugin for Hermes Agent: expressive text-to-speech, speech-to-text, voice library, cloning and voice design. | Python | 101 | 0 | Apache-2.0 | Oct 15 | Oct 15 |
By language
- Python 3
Related topics
- Whisper 3
- OpenAI 2
- Cross platform 2
- AI 2
- Hermes agent 2
- Python 2
- Real time 2
- macOS 2
- Text to speech 2
- Accessibility 1
- Agents 1
- AI memory 1
Read from GitHub by SpecStream between October 11, 2026 and October 15, 2026; each row shows the day its repository was read. Stars and pushes change every day, and the GitHub page is the current one. Forks and archived repositories are left out.