[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-1092":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":9,"totalLinesOfCode":9,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":9,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":22,"topics":9,"createdAt":9,"pushedAt":9,"updatedAt":24,"readmeContent":25,"aiSummary":26,"trendingCount":16,"starSnapshotCount":16,"syncStatus":14,"lastSyncTime":27,"discoverSource":28},1092,"freeflow","zachlatta\u002Ffreeflow","zachlatta","Free & fast alternative to Wispr Flow",null,"https:\u002F\u002Fgithub.com\u002Fzachlatta\u002Ffreeflow","Swift",1929,168,2,11,0,38,97,317,114,101.68,false,"main","2026-06-12 04:00:07","\u003Cp align=\"center\">\n  \u003Cimg src=\"Resources\u002FAppIcon-Source.png\" width=\"128\" height=\"128\" alt=\"FreeFlow icon\">\n\u003C\u002Fp>\n\n\u003Ch1 align=\"center\">FreeFlow\u003C\u002Fh1>\n\n\u003Cp align=\"center\">\n  Free and open source alternative to \u003Ca href=\"https:\u002F\u002Fwisprflow.ai\">Wispr Flow\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Fsuperwhisper.com\">Superwhisper\u003C\u002Fa>, and \u003Ca href=\"https:\u002F\u002Fmonologue.to\">Monologue\u003C\u002Fa>.\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fzachlatta\u002Ffreeflow\u002Freleases\u002Flatest\u002Fdownload\u002FFreeFlow.dmg\">\u003Cb>⬇ Download FreeFlow.dmg\u003C\u002Fb>\u003C\u002Fa>\u003Cbr>\n  \u003Csub>Works on all Macs (Apple Silicon + Intel)\u003C\u002Fsub>\n\u003C\u002Fp>\n\n---\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"Resources\u002Fdemo.gif\" alt=\"FreeFlow demo\" width=\"600\">\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ci>Thank you to \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmarcbodea\">@marcbodea\u003C\u002Fa> for maintaining FreeFlow!\u003C\u002Fi>\n\u003C\u002Fp>\n\n## Overview\n\nFreeFlow is a free Mac dictation app inspired by [Wispr Flow](https:\u002F\u002Fwisprflow.ai\u002F), [Superwhisper](https:\u002F\u002Fsuperwhisper.com\u002F), and [Monologue](https:\u002F\u002Fwww.monologue.to\u002F). It gives you fast AI transcription, context-aware cleanup, and voice-driven text editing without a monthly subscription.\n\n## Quick Start\n\n1. Download the app from above or [click here](https:\u002F\u002Fgithub.com\u002Fzachlatta\u002Ffreeflow\u002Freleases\u002Flatest\u002Fdownload\u002FFreeFlow.dmg)\n2. Get a free Groq API key from [groq.com](https:\u002F\u002Fgroq.com\u002F)\n3. Hold `Fn` to talk, or tap `Command-Fn` to start and stop dictation, and have whatever you say pasted into the current text field\n\n## Features\n\n- **Custom shortcuts:** Customize both hold-to-talk and toggle dictation shortcuts. If your toggle shortcut extends your hold shortcut, you can start in hold mode and press the extra modifier keys to latch into tap mode without stopping the recording.\n- **Context-aware cleanup:** FreeFlow can read nearby app context so names, terms, and phrases are spelled correctly when you dictate into email, terminals, docs, and other apps.\n- **Custom vocabulary:** Add names, jargon, and project-specific words that FreeFlow should preserve during cleanup.\n- **OpenAI-compatible providers:** Use Groq by default, or configure a custom model and API URL in settings.\n\n## Edit Mode\n\nEdit Mode lets you highlight existing text and transform it with a spoken instruction, like \"make this shorter\" or \"turn this into bullets.\" Enable it in settings, then use your normal dictation shortcut on selected text, or choose Manual mode to require an extra modifier key.\n\n## Privacy\n\nThere is no FreeFlow server, so FreeFlow does not store or retain your data. The only information that leaves your computer are API calls to your configured transcription and LLM provider.\n\n## Custom Cleanup\n\nIf you'd rather keep cleanup more literal and less context-aware, you can paste this simpler prompt into the custom system prompt setting:\n\n\u003Cdetails>\n  \u003Csummary>Simple post-processing prompt\u003C\u002Fsummary>\n\n  \u003Cpre>\u003Ccode>You are a dictation post-processor. You receive raw speech-to-text output and return clean text ready to be typed into an application.\n\nYour job:\n- Remove filler words (um, uh, you know, like) unless they carry meaning.\n- Fix spelling, grammar, and punctuation errors.\n- When the transcript already contains a word that is a close misspelling of a name or term from the context or custom vocabulary, correct the spelling. Never insert names or terms from context that the speaker did not say.\n- Preserve the speaker's intent, tone, and meaning exactly.\n\nOutput rules:\n- Return ONLY the cleaned transcript text, nothing else. So NEVER output words like \"Here is the cleaned transcript text:\"\n- If the transcription is empty, return exactly: EMPTY\n- Do not add words, names, or content that are not in the transcription. The context is only for correcting spelling of words already spoken.\n- Do not change the meaning of what was said.\n\nExample:\nRAW_TRANSCRIPTION: \"hey um so i just wanted to like follow up on the meating from yesterday i think we should definately move the dedline to next friday becuz the desine team still needs more time to finish the mock ups and um yeah let me know if that works for you ok thanks\"\n\nThen your response would be ONLY the cleaned up text, so here your response is ONLY:\n\"Hey, I just wanted to follow up on the meeting from yesterday. I think we should definitely move the deadline to next Friday because the design team still needs more time to finish the mockups. Let me know if that works for you. Thanks.\"\u003C\u002Fcode>\u003C\u002Fpre>\n\u003C\u002Fdetails>\n\n## FAQ\n\n**Why does this use Groq instead of a local transcription model?**\n\nI love this idea, and originally planned to build FreeFlow using local models, but to have post-processing (that's where you get correctly spelled names when replying to emails \u002F etc), you need to have a local LLM too.\n\nIf you do that, the total pipeline takes too long for the UX to be good (5-10 seconds per transcription instead of \u003C1s). I also had concerns around battery life.\n\nSome day!\n\n**Update:** You can now use a custom model with FreeFlow by configuring the LLM API URL in the FreeFlow settings to use Ollama. Thank you @taciturnaxolotl!\n\n## License\n\nLicensed under the MIT license.\n","FreeFlow 是一款免费的Mac语音听写应用，灵感来源于Wispr Flow、Superwhisper和Monologue。其核心功能包括快速AI转录、上下文感知的文本清理以及无需订阅即可使用的语音驱动文本编辑。该应用支持自定义快捷键设置，允许用户根据个人习惯调整启动和停止听写的按键组合；同时具备识别并正确拼写特定名称或术语的能力，确保在邮件、文档等不同应用场景中保持高准确性；此外还兼容OpenAI格式的第三方模型，为用户提供更多选择。FreeFlow适用于需要高效完成文档编写、邮件回复等任务的场景，尤其适合频繁使用语音输入的用户。","2026-06-11 02:41:33","trending"]