Two hand-approved projects in our catalog replace Wispr Flow. Both are audio software. Voicebox has the most GitHub stars (59.1K). Tick what matters to you and the list re-sorts so the closest fits come first.
What matters to you?
Each choice is checked against live catalog data. Counts show how many alternatives meet it.
Licence
Activity
Language
Catalog
The alternatives
Pick what matters below. For now the two alternatives are in order of GitHub stars.
Clone voices, generate speech and dictate, all on your own computer.
Clones voices from audio samples using engines such as Qwen3-TTS, Chatterbox and Kokoro.
Dictates with a global hotkey, using Whisper and an optional local clean-up model.
Lets MCP-aware agents such as Claude Code and Cursor speak in a chosen voice.
Meets: Permissive licenceMeets: Open-source licenceDoes not meet: Released ≤ 90 daysDoes not meet: Gaining starsMeets: Written in PythonMeets: In a stack
Private voice dictation that works across your Mac.
Transcribe speech locally through configurable global and push-to-talk shortcuts
Apply app-aware modes, screen context, writing styles, and smart text cleanup
Teach custom vocabulary and replacements or switch into voice assistant mode
Does not meet: Permissive licenceMeets: Open-source licenceMeets: Released ≤ 90 daysMeets: Gaining starsMeets: Written in SwiftDoes not meet: In a stack
Data from GitHub and our catalog. Every listing is hand-approved. List prices are what the vendor publishes, not a quote, and self-hosting has its own running costs.
