Show HN: Freestyle – Wispr Flow Alternative that respects privacy

Freestyle, a free and open-source dictation app that converts voice to text locally, launched as a privacy-focused alternative to Wispr Flow. The app supports multiple AI providers and runs on-device models to ensure dictations never leave the user's device.

Freestyle is the dictation app that converts your voice into text. Hold down a hotkey, talk, and clean text will appear wherever your cursor is. Speak 4X faster than you type. Freestyle is free, open source, and local-first. Run a local model and your dictations never leave your device, or bring your own API key when you'd rather use a cloud provider. Voice dictation — hold the hotkey, speak, release to paste at your cursor in milliseconds. Choose your model provider — OpenAI, Groq, Anthropic, Google, Deepgram, ElevenLabs. Bring your own API key. Transcription cleaning — grammar and punctuation cleanup via post-processing. No more "um, oh, but". Dictionary — custom phrase replacements applied after transcription. ex. "type script" → TypeScript . Contextual correction — reformat your text based on where you're typing. Automatically format emails into email format. | Platform | Download | |---|---| | macOS Apple Silicon | .dmg | .dmg .exe / https://github.com/freestyle-voice/freestyle/releases/latest .AppImage .deb Contributions are welcome. See CONTRIBUTING.md /freestyle-voice/freestyle/blob/main/CONTRIBUTING.md for setup, local development, and opening up a PR. Consider joining our Discord server https://discord.gg/Fmgt5yZCDu That's where project contributors communicate.