Voice Keyboard
Speech-to-text keyboard that uses your own Whisper API key
新版本 1.10.0
Voice input for other apps: optional Android recognition service and dictation window using your saved provider. New compact Terminal panel, off by default, with full-size touch targets and instant expansion. Cancel the latest dictation during recording, recognition, post-processing or retry without interrupting earlier recordings. Enable the new options in Advanced settings. Recognition requires a connection to your provider; apps using their own speech engine may not use it.
Voice Keyboard is a keyboard that types what you say. Switch to it in any text field, tap the microphone, speak, and the text lands in whatever app you are using.
It has no speech engine of its own and no account. Bring an API key for a supported speech service, such as Groq or Mistral, or run a server of your own. Audio goes only to the endpoint you configure. Compatible Chat Completions services can also transcribe audio; the selected model must accept your device's recording format.
Voice input
Optional post-processing
Keyboard
Privacy
The app can also look for new versions on GitHub: automatically only if you switch that on, or when you press "Check for updates". Updates obtained that way come straight from the developer and are not reviewed by F-Droid.
It has no speech engine of its own and no account. Bring an API key for a supported speech service, such as Groq or Mistral, or run a server of your own. Audio goes only to the endpoint you configure. Compatible Chat Completions services can also transcribe audio; the selected model must accept your device's recording format.
Voice input
- Works in any text field, in any app
- Processing queue: start the next recording while the previous one is still being transcribed
- Cancel only the latest unfinished dictation during recording, recognition, post-processing or retry; earlier recordings continue
- Optional voice input for other apps through Android speech recognition or a dictation window. Off by default, uses your saved provider, without post-processing or context
- Offline-proof keyboard dictation: a recording that cannot be sent is kept on the device and resent automatically once the connection returns
- Several dictation languages on one key: tap to cycle, long-press to pick from the list
- Custom vocabulary for names and technical terms that get misrecognised
- Can be the voice input of another keyboard, such as HeliBoard, and hand back to it once the text is typed
Optional post-processing
- Fix punctuation, spelling and filler words
- Shorten, add emoji, rewrite as verse, or translate
- Optional recent dictation context helps recover misheard names and terms. Off by default; remembers up to 5 of your own recent dictations only in memory and sends them to the selected provider as reference. Context is shared across chats in the same app and clears when input moves to another app. It does not read conversations.
- Terminal mode turns dictation into shell commands
- Works with OpenAI, Anthropic, or any OpenAI-compatible provider such as OpenRouter; every prompt is editable
Keyboard
- One tap takes you back to the keyboard you came from
- Optional compact Terminal panel with full-size controls and instant expansion; off by default
- Punctuation keys, accelerating backspace, send key, persistent clipboard bar
- The Enter key runs the field's own action: Search, Go, Send, Next or Done
- The microphone is off in password fields
- Spacing around dictated text follows the text already in the field
- Light, dark and automatic themes; 17 interface languages
Privacy
- No analytics, no advertising, no tracking, no account, no servers of our own
- API keys and settings stay on the device and are excluded from cloud backup
- Audio is sent only to the endpoint you configured, authenticated with your own key
The app can also look for new versions on GitHub: automatically only if you switch that on, or when you press "Check for updates". Updates obtained that way come straight from the developer and are not reviewed by F-Droid.
负面特征
此应用有一些你未必喜欢的特征。 了解更多！
捐赠
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-
arm64-v8aarmeabi-v7ax86x86_64该版本需要 Android 7.0 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。
-
arm64-v8aarmeabi-v7ax86x86_64该版本需要 Android 7.0 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。
-
arm64-v8aarmeabi-v7ax86x86_64该版本需要 Android 7.0 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。
新版本 1.9.9
Optional recent dictation context helps post-processing recover misheard names and terms when earlier wording strongly matches. Off by default; sends up to 5 of your own recent dictations to your chosen provider. Kept only in memory, shared across chats in the same app, and cleared on app/private-field changes, disabling, 30 minutes idle or restart. No conversations are read. Terminal mode does not use or add context.