{"full_name":"altic-dev/FluidVoice","owner":"altic-dev","name":"FluidVoice","shard":"1","url":"https://github.com/altic-dev/FluidVoice","description":"Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. Windows, iOS testflight!  Android, Linux waitlist open! A local Wispr Flow alternative. Follow https://x.com/fluidvoiceapp for more","homepage":"https://altic.dev/fluid","topics":["ai","dictation","ios","llama-cpp","macos","swift"],"tag_pages":["ai","ios","llama-cpp","macos","swift"],"language":"Swift","license":"GPL-3.0","avatar":"https://avatars.githubusercontent.com/u/224717674?u=b66617cc95018c5bc081ae6f0c4106631bf65422&v=4","created_at":"2025-09-21T17:35:02Z","pushed_at":"2026-11-16T05:14:01Z","metrics":{"stars":13088,"forks":987,"watchers":47,"issues":701,"prs":477,"releases":66,"issues_open":88,"issues_closed":613,"prs_open":39,"prs_closed":165,"prs_merged":273,"discussions":163},"growth":{"day":{"stars":358,"forks":53,"base_day":"2026-11-04"},"week":{"stars":358,"forks":53,"base_day":"2026-11-04"},"month":{"stars":1068,"forks":120,"base_day":"2026-10-17"}},"history":{"dates":["2026-09-06","2026-09-07","2026-09-08","2026-09-09","2026-09-10","2026-09-11","2026-09-12","2026-09-13","2026-09-14","2026-09-15","2026-09-16","2026-09-17","2026-09-18","2026-09-19","2026-09-20","2026-09-21","2026-09-22","2026-09-23","2026-09-24","2026-09-25","2026-09-26","2026-09-27","2026-09-28","2026-09-29","2026-09-30","2026-10-01","2026-10-02","2026-10-03","2026-10-04","2026-10-05","2026-10-06","2026-10-07","2026-10-08","2026-10-09","2026-10-10","2026-10-11","2026-10-12","2026-10-13","2026-10-14","2026-10-15","2026-10-16","2026-10-17","2026-10-18","2026-10-19","2026-10-20","2026-10-21","2026-10-22","2026-10-23","2026-10-24","2026-10-25","2026-10-26","2026-10-27","2026-10-28","2026-10-29","2026-10-30","2026-10-31","2026-11-01","2026-11-02","2026-11-03","2026-11-04","2026-11-16"],"stars":[10870,10908,10941,10971,11001,11022,11059,11171,11197,11226,11249,11262,11308,11336,11352,11402,11439,11465,11533,11554,11585,11611,11627,11644,11677,11697,11717,11734,11758,11771,11810,11827,11867,11882,11894,11913,11926,11942,11959,11971,11978,12020,12050,12088,12193,12230,12254,12295,12322,12340,12391,12418,12439,12464,12520,12570,12599,12613,12670,12730,13088],"forks":[746,750,755,757,762,762,767,778,783,790,789,792,798,804,809,813,816,820,820,823,825,828,831,833,836,836,839,840,842,843,847,852,860,862,862,863,863,865,867,865,866,867,869,873,882,887,889,892,893,897,899,902,904,907,910,913,918,920,919,934,987],"watchers":[49,51,50,50,50,48,48,49,49,49,49,49,50,50,50,50,50,50,51,51,50,50,50,49,49,50,50,51,51,51,51,51,51,50,50,50,51,51,50,50,50,50,50,50,50,50,50,49,50,49,49,49,47,47,47,47,47,47,47,47,47],"issues_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,88],"prs_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,39]},"boards":{"daily":67,"daily_rate":65,"daily_forks":68},"same_owner":[],"issues":[{"number":925,"title":"[BUG] Fluid Intelligence is unusably slow","comments":19,"created_at":"2026-09-01T08:52:22Z"},{"number":852,"title":"[BUG] Dictation stops detecting microphone input after 3 seconds","comments":19,"created_at":"2026-08-13T03:40:25Z"},{"number":479,"title":"Dictated list not inserted in Claude Code under cmux — only \"a\" appears (transcript correct; VS Code works)","comments":16,"created_at":"2026-06-29T15:24:04Z"},{"number":1273,"title":"[BUG] Transcription, not pasting in","comments":15,"created_at":"2026-11-02T15:02:10Z"},{"number":909,"title":"Return Key M5 Mac OS26.5.1 in ver 1.6.9 opens Dictate fcn","comments":11,"created_at":"2026-08-27T17:01:33Z"},{"number":736,"title":"[BUG] Cohere Transcribe truncates audio (with fix)","comments":11,"created_at":"2026-07-29T17:53:03Z"},{"number":1229,"title":"[BUG] FluidMeet cannot detect inbound call speaker(s)","comments":10,"created_at":"2026-10-23T17:05:44Z"},{"number":948,"title":"[BUG] FluidVoice accumulates high idle CPU over a long session (204 min CPU time in ~17 h uptime) — M4 Pro","comments":10,"created_at":"2026-09-07T14:03:55Z"}],"discussions":[{"number":1349,"title":"Optional idle unloading for larger speech models","comments":0,"category":"Ideas","created_at":"2026-11-15T17:54:07Z"},{"number":1339,"title":"Allow importing of audio files for transcription/diarisation","comments":0,"category":"Ideas","created_at":"2026-11-14T02:45:36Z"},{"number":1331,"title":"Add ElevenLabs Scribe as an optional Voice Engine for dictation","comments":0,"category":"Ideas","created_at":"2026-11-13T13:53:37Z"},{"number":1330,"title":"FluidVoice 1.6.13 crashes on launch on macOS 27.2","comments":0,"category":"General","created_at":"2026-11-13T12:56:15Z"},{"number":1319,"title":"External Teams-to-Browser Transition Causes Silent Loss of Participant Audio Recording","comments":0,"category":"Ideas","created_at":"2026-11-12T17:36:21Z"},{"number":1318,"title":"Per-app lowercase formatting without an AI provider","comments":0,"category":"Ideas","created_at":"2026-11-11T14:42:17Z"},{"number":1317,"title":"AssemblyAI Dictation as a cloud transcription option","comments":0,"category":"Ideas","created_at":"2026-11-11T13:33:56Z"},{"number":1315,"title":"Loving FluidVoice! Best way to keep one Custom Dictionary on two Macs?","comments":1,"category":"Q&A","created_at":"2026-11-11T03:56:31Z"}],"latest_release":{"name":"FluidVoice v1.6.13","tag":"v1.6.13","published_at":"2026-11-13T11:25:26Z","body":"# FluidVoice v1.6.13\n\n## What's New\n\n- Fluid 1.1 Ripple and Splash: updated on-device cleanup, with Ripple offering a faster alternative to Splash. Both are research previews; review your text before sending.\n- Fluid Speech Pro: our most accurate local dictation model for Apple Silicon. Pro, Mini and Pico support 25 languages.\n- Edit Mode (Beta): a dedicated Edit 1.1 model on Apple Silicon, with settings separate from dictation and continued support for your own API providers.\n- Qwen3 ASR 1.7B: on-device dictation on Apple Silicon with automatic detection of 30 languages.\n- Apple Intelligence for Command Mode: use Apple's on-device model on supported Macs running macOS 27 or later.\n\n## Improvements\n\n- Compact, consistent start and end prompts with visible countdowns and clearer button feedback.\n- Detected calls stop recording after a cancellable countdown. Muting or losing a call window no longer ends an active recording prematurely.\n- Automatic captures computer audio and your microphone, including when recording again. Online meetings no longer silently switch to microphone-only recording.\n- Choose the meeting app and microphone before recording, with recent choices first and better handling of disconnected microphones and restarted apps.\n- Rename meetings while recording. Renaming a saved meeting keeps its summary.\n- Meeting transcripts use Fluid Speech Pro with an available Parakeet fallback. Redo a finished transcript in another supported language using its saved audio.\n- Saved dictionary replacements now apply to completed meeting transcripts. Redo also refreshes replacements, with improved English number and currency formatting.\n- Smoother live captions with Reduce Motion support. Local tools can also read live captions through the local API.\n- More consistent formatting for spoken quantities and currencies, plus named emoji, while preserving code, filenames and identifiers.\n- Accepted dictionary corrections save their audio and original/corrected text locally for future training. Nothing is uploaded, and FluidVoice tells you if audio cannot be saved.\n- Choose how soon dictionary suggestions appear, without repeated delays while editing.\n- Dashboard recommends speech and cleanup models for your Mac, with download-and-activate actions and dismissible suggestions.\n- AI Providers is now AI Settings, with clearer Edit Mode and Cleanup Styles controls. Restoring older settings preserves your Edit provider.\n- Choose an Apple Speech language and region on macOS 26 or later.\n- Choose your own accent color in Settings.\n- New recording sounds and stop cues, with sound settings now under Dictation.\n- Shortcuts now distinguish left and right modifier keys. Re-record existing shortcuts to choose a specific side.\n- Fluid Intelligence screen context is off by default, with optional setup and a reminder to review AI changes.\n\n## Fixes\n\n- Preserve opening speech, short replies and sentence endings, with more readable overlapping speech and fewer duplicate words.\n- Reduce false incomplete-transcription warnings during normal recording startup and shutdown.\n- Keep previous transcripts when redo fails or is interrupted, and keep loaded meeting history visible if saved files cannot be read.\n- Improved Google Meet detection and more reliable saved recording preferences.\n- Trained words keep working after reloading Fluid Speech Pro.\n- Better first-word recognition in short Parakeet dictations, with fixes for skipped short audio and final snippets.\n- More reliable pasting and recovery in slow editors, web editors and consecutive dictations. Undelivered text stays on the clipboard for manual recovery.\n- Improved text-field detection in Electron apps and restored dictation in Muse.\n- Verify, update or delete downloaded cleanup models without activating them first. The active model stays clearly marked.\n- More reliable model downloads, automatic retries for interrupted speech downloads, and uninterrupted setup when resizing Dashboard.\n- Better al","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}