DeepSeek Harness Remote
DeepSeek Harness Remote 可將手機或另一台電腦與你運行 DeepSeek Harness 的電腦安全連接,隨時隨地繼續你的工作,方便隨時查看進度並繼續工作。
AI 翻譯
尚未偵測到更新。GitHub 發布版本後會顯示在這裡。
個人 GitHub 帳號下公開儲存庫的擁有者可以登入並驗證所有權,自行管理介紹,無需管理員核准。
登入並產生驗證檔案,在 30 分鐘內將其提交至此儲存庫的預設分支。其他分支或分叉儲存庫中的檔案無效。然後在下方檢查檔案,即可無需管理員核准直接管理專案。請保留檔案以維持管理權限。
如需登入,將前往登入頁面。登入後請回到此處,再次點擊所選的驗證按鈕。
在專案資料夾中執行 /nomorevibe verify,即可驗證所有權並自行管理介紹。
一分鐘完成驗證製作者的介紹僅有上面的一句話。 更多詳情請閱讀儲存庫 README。 儲存庫 README ↗
正在載入完整 README。
檢視完整 README ↗FreeFlow is a free Mac dictation app inspired by Wispr Flow, Superwhisper, and Monologue. It gives you fast AI transcription, context-aware cleanup, and voice-driven text editing without a monthly subscription.
Fn to talk, or tap Command-Fn to start and stop dictation, and have whatever you say pasted into the current text fieldEdit 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.
There 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.
If you'd rather keep cleanup more literal and less context-aware, you can paste this simpler prompt into the custom system prompt setting:
FreeFlow can use OpenAI-compatible local or self-hosted providers instead of Groq. In settings, configure the API base URL and model IDs for your local LLM provider, such as Ollama, LM Studio, or another OpenAI-compatible server. If your transcription backend uses a different endpoint from your LLM backend, set the transcription API URL separately.
Local models are often slower than hosted providers, especially on cold start, long recordings, or busy hardware.
FreeFlow keeps the default network timeout at 20 seconds, but you can extend it with macOS defaults. One exception applies only to Groq's own endpoint (https://api.groq.com/openai/v1): cleanup of a new dictation waits at most 2.5 seconds. If cleanup misses that, FreeFlow pastes your transcript with local formatting and the Run Log shows "Cleanup timed out, using raw transcript". Any other API base URL, including local models, keeps 20 seconds, and so do Edit Mode, dictations with an Output Language, and Run Log retries.
defaults write com.zachlatta.freeflow transcription_timeout_seconds -float 120
defaults write com.zachlatta.freeflow post_processing_timeout_seconds -float 120
defaults write com.zachlatta.freeflow context_request_timeout_seconds -float 120
The timeout keys are:
transcription_timeout_seconds: audio transcription requestspost_processing_timeout_seconds: transcript cleanup and edit mode requests; a positive value also replaces the 2.5-second Groq dictation cleanup budgetcontext_request_timeout_seconds: nearby app context requestsOnly positive values are used. Remove a custom timeout to return to the defaults:
defaults delete com.zachlatta.freeflow transcription_timeout_seconds
defaults delete com.zachlatta.freeflow post_processing_timeout_seconds
defaults delete com.zachlatta.freeflow context_request_timeout_seconds
See CONTRIBUTING.md for how to set up the project, build, test, and submit changes.
Licensed under the MIT license.