AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Customer Support › VoiceFlow
✦ Free & open sourceCustomer Support

VoiceFlow

Local voice dictation and meeting recorder with Whisper and BYO-LLM.

Local Voice Dictation and Meeting Recorder

Offline speech-to-text with system audio capture and bring-your-down LLM summaries.

Free forever · open source · MIT
✓ Use today✓ Browser-based✓ Real-time collaboration
5.5
ZEKAI
Private local voice dictation
Free & open source · Customer Support
Ease of setup2
Usefulness8
Maintenance7
Community5
★ 436
GITHUB
Jun 2026
UPDATED
MIT
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

VoiceFlow is a local voice dictation and meeting recorder for Windows and Linux that runs entirely on your machine. You should use it if you want fast speech-to-text without sending your voice or meeting data to cloud transcription services.

Runs on
Cross-platform
Hosting
Desktop
Languages
Python
License
MIT

What it is

The application lives in your system tray, letting you hold a hotkey to dictate directly at your cursor via faster-whisper. It also records long-form meetings capturing both your microphone and system audio into a stereo file for local transcription and optional LLM summaries.

Who it's for

It suits professionals who handle sensitive customer calls or prefer privacy-first dictation without monthly subscriptions. It does not suit heavy macOS users since macOS builds are currently unsupported.

Key features

System Audio Capture

Captures both your microphone and system audio into a single stereo file during long-form meetings.

Local Whisper Inference

Runs transcription locally on your machine using faster-whisper with automatic CUDA acceleration when available.

Bring Your Own LLM

Summarizes meeting recordings using OpenAI, Groq, OpenRouter, Ollama, or any OpenAI-compatible endpoint.

Searchable History

Stores a local SQLite log of every transcript directly on your machine for easy retrieval and search.

Multiple Export Formats

Exports your transcripts and recordings to Markdown, plain text, SRT, or structured JSON files.

How to start

Up and running in 3 steps

1
Grab the latest binary installer for Windows or AppImage/tar.gz for Linux from the GitHub releases page
2
Complete the first-launch setup wizard to configure your microphone, compute device, and download a Whisper model
3
Hold your chosen global hotkey to dictate or use the dashboard to record long-form meetings
Real talk

Our honest verdict

What's great

  • Audio stays entirely in your RAM and local machine without sending data to cloud servers
  • Supports 16+ Whisper models including tiny, large-v3, distilled, and .en variants
  • Re-transcribe saved recordings using different models or languages without re-recording
  • Built-in playback via URL schemes lets you jump straight from transcript lines to audio

Where it falls short

  • macOS builds run but are not officially supported yet
  • Requires local hardware resources like a CUDA-capable GPU for fast large-model transcription
  • LLM summaries require your own API keys or a local instance like Ollama
Cost

Pricing & license

VoiceFlow is free under its open-source license. The only running costs depend on whether you use paid cloud LLM providers for meeting summaries or run models locally for free.

Paid work

Open remote AI-training roles

877 open remote AI-training roles, updated November 16, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

Get more

Use it, or have us set it up

📄 Free PDF: VoiceFlow for Customer Support
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure VoiceFlow for you — and train your team.
Get it done for you ↗
Questions

FAQ

Does VoiceFlow require an internet connection?

No, transcription and dictation run entirely offline. An internet connection is only needed if you choose to send meeting summaries to a cloud-based LLM provider.

Where are my transcripts and audio files saved?

All transcripts are stored locally in a SQLite database located at ~/.VoiceFlow/ on your machine.

Can I use custom LLM endpoints for summaries?

Yes, you can use OpenAI, Groq, OpenRouter, Ollama, or any OpenAI-compatible endpoint with API keys stored securely in your OS keychain.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Customer Support — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google