Audio
MockingBird
🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time
★ 36.9k starsUnknown
View guide →// audio · crosswk/SayIt
SayIt
SayIt is an open-source audio project by crosswk (crosswk/SayIt on GitHub). It has 427 GitHub stars and 63 forks, is released under the AGPL-3.0 license, and was last updated on GitHub on 30 September 2026.
Open source voice typing for Windows — a Wispr Flow / Superwhisper alternative.
💎 Hidden gem★ 427 stars⑂ 63 forksAGPL-3.0updated 2026-09
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- crosswk/SayIt
- GitHub stars
- 427
- Forks
- 63
- License
- AGPL-3.0
- Last updated on GitHub
- 30 September 2026
- Category
- Audio
- Listing
- Hidden gem — a shorter page for a lesser-known project
- Official site
- Official site
// how it works
How it works
- Follow the quickstart
The README documents setup; start with the install section.
- Pick your use case
Decide what you want SayIt to do first — open source voice typing for Windows — a Wispr Flow / Superwhisper alt.
- Check for updates
Pull the latest changes to stay current with fixes.
- Make it yours
Change the config to match your workflow, then run it daily.
// features
Why people love it
Asr
Working asr support built in.
Dictation support
Type by speaking anywhere.
Gguf
Working gguf support built in.
Local-first design
Your data stays on your machine.
TypeScript codebase
Typed code that is easier to maintain.
AGPL-3.0 license
Free to use; network services stay open.
Advertisement
// run it
Run it yourself
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/crosswk/SayIt.git cd sayit - Step 2 — Install
Install the Node dependencies.
npm install - Step 3 — Run it
Start the app or dev server.
npm start
// use cases
What you can build
- Clean up and process recorded audio locally.
- Turn voice memos into searchable text.
- Dictate notes hands-free on your machine.
- Build a voice-controlled feature for an app.
Advertisement
// faq
Questions, answered
Is SayIt free to use?
Yes, but note the copyleft: it is AGPL-3.0 licensed, so distributed derivatives must stay open.
Do I need an account to use SayIt?
No. It is a self-run project — clone it and run it on your own machine. Some features may optionally call external APIs; check the README.
Can I run SayIt on my own hardware?
Yes, that is the point. The code is public, so you can run, modify, and host it yourself.
How is SayIt licensed?
It is released under AGPL-3.0. Read the LICENSE file in the repo for the exact terms.
Is the project still maintained?
The repo shows activity as of 2026-09-30. Check the commit history and open issues on GitHub to judge how active maintenance is right now.
// keep exploring
Similar tools
Audio
TranscriptionSuite
Fully local transcription with diarization, for every desktop OS.
★ 759 starsGPL-3.0
View guide →Audio
agentcall
AgentCall lets AI Agents join meetings with voice
★ 164 starsMIT
View guide →Audio
tambourine-voice
Your personal voice interface for any app — open Wispr Flow alternative.
★ 389 starsAGPL-3.0
View guide →Audio
opentypeless
Open-source AI voice typing: hotkey, speak, get polished text anywhere.
★ 582 starsMIT
View guide →Audio
SpeakoFlow
Free and open source offline voice dictation for Windows, Linux, and macOS.
★ 259 starsMIT
View guide →// alternatives
Alternatives in Audio
The most-starred other Audio projects in the LibreAI catalogue — the realistic shortlist if SayIt is not the right fit.
- MoneyPrinterTurbo★ 128.3k
利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.
- Whisper★ 109.9k
Robust Speech Recognition via Large-Scale Weak Supervision
- GPT-SoVITS★ 62.3k
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
- Real-Time-Voice-Cloning★ 60.2k
Clone a voice from 5 seconds of audio and generate arbitrary speech in real time
- whisper.cpp★ 54.1k
Port of OpenAI's Whisper model in C/C++
// more in audio
More in Audio
Nearby Audio projects in the catalogue, closest in stars to SayIt — keep exploring the shelf either side of it.
- ChatTTS-OpenVoice★ 466
Fuse ChatTTS with OpenVoice: clone a voice from a 10-second clip.
- tambourine-voice★ 389
Your personal voice interface for any app — open Wispr Flow alternative.
- TeroSubtitler★ 467
Free, cross-platform subtitle editor with AI transcription tools.
- izwi★ 385
Local-first voice AI runtime: transcription, diarization, TTS, cloning.
- talk-to-fengge★ 469
Clone anyone's voice and personality for real-time conversation.
- subtitler★ 379
Free on-device web app that transcribes audio and renders subtitles.
Get SayIt
Free and open — grab the source, star the repo, and start creating.