Polished Recognition
Voice input for any keyboard — transcribe with your own API endpoints
Polished Recognition is a voice keyboard powered by your own AI. Switch to it, speak, and polished text lands in whatever app you are typing in — transcribed by the speech provider you choose, refined by the language model you choose, with a prompt you write.
Switch to the Polished keyboard and recording starts instantly. Pause and resume mid-sentence, switch to your typing keyboard and back without losing dictation, then tap send: audio goes to your STT provider, the LLM polishes the text — fixing filler words and punctuation, restructuring, or translating to another language — and flawless text is typed into the field. Raw mode skips the LLM entirely and inserts the plain transcription; Polish only refines without translating.
Bring your own provider. 18 presets (OpenAI, GROQ, OpenRouter, Google AI, DeepSeek, xAI, Mistral, local Ollama/LM Studio, …) or any custom OpenAI-compatible endpoint. GROQ's free tier covers a complete STT-plus-polish pipeline at zero cost. The system prompt is fully editable, with variables for source and target language; searchable model pickers with per-provider caching handle hundreds of models.
Gboard will never use this. Gboard's microphone is hardcoded to Google's voice typing and cannot be redirected to any third-party voice input. Use a keyboard that delegates its mic: the AOSP keyboard (LineageOS and derivatives), HeliBoard (F-Droid only), Fossify Keyboard, or OpenBoard.
Privacy-first: No analytics, no tracking, no proprietary SDKs, no account, no central server. All data flows directly between your device and your chosen endpoints — or nowhere at all, if you run Ollama locally.
Permissions:
• RECORD_AUDIO — required to capture microphone input
• INTERNET — required to send audio to your configured STT/LLM endpoints
Switch to the Polished keyboard and recording starts instantly. Pause and resume mid-sentence, switch to your typing keyboard and back without losing dictation, then tap send: audio goes to your STT provider, the LLM polishes the text — fixing filler words and punctuation, restructuring, or translating to another language — and flawless text is typed into the field. Raw mode skips the LLM entirely and inserts the plain transcription; Polish only refines without translating.
Bring your own provider. 18 presets (OpenAI, GROQ, OpenRouter, Google AI, DeepSeek, xAI, Mistral, local Ollama/LM Studio, …) or any custom OpenAI-compatible endpoint. GROQ's free tier covers a complete STT-plus-polish pipeline at zero cost. The system prompt is fully editable, with variables for source and target language; searchable model pickers with per-provider caching handle hundreds of models.
Gboard will never use this. Gboard's microphone is hardcoded to Google's voice typing and cannot be redirected to any third-party voice input. Use a keyboard that delegates its mic: the AOSP keyboard (LineageOS and derivatives), HeliBoard (F-Droid only), Fossify Keyboard, or OpenBoard.
Privacy-first: No analytics, no tracking, no proprietary SDKs, no account, no central server. All data flows directly between your device and your chosen endpoints — or nowhere at all, if you run Ollama locally.
Permissions:
• RECORD_AUDIO — required to capture microphone input
• INTERNET — required to send audio to your configured STT/LLM endpoints
- 作者: Georg Graf
- 许可: MIT License
- 问题跟踪系统
- 源代码
- 更新日志
- 构建元数据
- 可重复性状态
版本
尽管下面提供了 APK 安装包的下载选项，但你应该注意，以这种方式安装将不会收到更新通知，这是一种不太安全的下载方式。 我们建议你安装使用 F-Droid 客户端。
下载 F-Droid-
该版本需要 Android 11 及以上版本。
此包由原始开发者构建并签名，并保证对应于此源代码 tarball。
-
该版本需要 Android 11 及以上版本。
此包由原始开发者构建并签名，并保证对应于此源代码 tarball。
-
该版本需要 Android 11 及以上版本。
此包由原始开发者构建并签名，并保证对应于此源代码 tarball。