# altic-dev/FluidVoice

Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. Windows pre-build available! A local Wispr Flow alternative. DM us on X for an easter egg 😉 - https://x.com/fluidvoiceapp

Repository: https://github.com/altic-dev/FluidVoice
Canonical: https://ross.abutalabs.com/products/fluidvoice
Homepage: https://altic.dev/fluid
Language: Swift
License: GPL-3.0
License Family: copyleft
Topics: ai, dictation, ios, llama-cpp, macos, swift
Last push: 2026-08-26T22:13:11+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 98, longevity 24
- inputs: {"age_days": 346, "days_push": 7, "days_rel": 15, "gap_med": 6.0, "n_releases_24m": 39}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 10946, forks 755 (observed 2026-08-28T04:10:44.746895+00:00)

## What it is
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
- artifact type: application
- maturity: active
- function: speech-recognition, nlp, llm-inference, gui
- domain: speech-processing, developer-tools, desktop-applications, privacy
- platform: -
- tags: dictation, voice-to-text, on-device, whisper, parakeet, wispr-flow-alternative, local-ai, accessibility, natural-language-processing, macos, desktop, swift

## Member repositories
- altic-dev/FluidVoice (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:44.746895+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:17:18.662498+00:00, confidence not recorded.
  - readme: https://github.com/altic-dev/FluidVoice (fetched 2026-08-28T04:10:44.746895+00:00, sha b6b945457578)
  - homepage: https://altic.dev/fluid (fetched 2026-08-29T08:15:59.086891+00:00, sha 9e0b047ab7a0)
- Data as of 2026-08-30T08:39:29.467469+00:00.