altic-dev/FluidVoice

Health v2 · maintenance only

Adoption not part of the score

10946 stars · 755 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

FluidVoice is an open-source (GPLv3) macOS dictation app that transcribes speech to text entirely on-device using models like Parakeet, Whisper, and Apple Speech. It includes a custom-trained local AI enhancement model (Fluid-1/Fluid Intelligence) that polishes raw transcripts into formatted, ready-to-send text without any cloud calls.

Use cases

• dictate text into any app with a hotkey
• transcribe speech locally without sending audio to the cloud
• turn rambling voice notes into polished emails or prompts
• replace Wispr Flow with a free open-source alternative
• voice-type coding prompts into terminal tools like Claude Code
• smart formatting and capitalization of dictated text

When to choose

• you need privacy-first dictation with zero data leaving your machine
• you want the fastest possible on-device speech-to-text on Apple Silicon or Intel Macs
• you want AI-enhanced transcription without API keys or subscriptions
• you prefer open-source, self-contained desktop software

When to avoid

• you need iOS, Windows, or Linux support today (only macOS builds are current)
• you need cloud-scale or multi-user transcription services
• you require a permissive license for proprietary redistribution (GPLv3)
• you need speaker diarization or audio file batch transcription

Facets

application · maturity active

speech-recognition nlp llm-inference gui speech-processing developer-tools desktop-applications privacy dictation voice-to-text on-device whisper parakeet wispr-flow-alternative local-ai accessibility natural-language-processing macos desktop swift

Member repositories

For agents

markdown · JSON · MCP: product_card(name="altic-dev/FluidVoice")