{"package_name":"com.tyraen.voicekeyboard","name":"Voice Keyboard","summary":"Speech-to-text keyboard that uses your own Whisper API key","category":"Keyboard & IME","icon_url":"/api/icon/com.tyraen.voicekeyboard","latest_version_code":58,"latest_version_name":"1.9.7","apk_url":"/api/apk/com.tyraen.voicekeyboard","apk_size":2872229,"apk_sha256":"1f8b7afad8b679931f8950d5bd4fefc073c0139c276c54b8282b3c668b7f2e33","source_kind":"fdroid-repo","repo_slug":"fdroid-main","last_updated":1792033249,"release_timestamp":1791945534,"description":"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.\n\nIt has no speech engine of its own and no account. You bring an API key for an OpenAI-compatible Whisper endpoint — Groq and Mistral both offer a free tier — or run a server of your own, and your audio goes to that endpoint and nowhere else.\n\n<b>Voice input</b>\n<ul><li>Works in any text field, in any app</li><li>Processing queue: start the next recording while the previous one is still being transcribed</li><li>Offline-proof: a recording that cannot be sent is kept on the device and resent automatically once the connection returns</li><li>Several dictation languages on one key: tap to cycle, long-press to pick from the list</li><li>Custom vocabulary for names and technical terms that get misrecognised</li><li>Can be the voice input of another keyboard, such as HeliBoard, and hand back to it once the text is typed</li></ul>\n\n<b>Optional post-processing</b>\n<ul><li>Fix punctuation, spelling and filler words</li><li>Shorten, add emoji, rewrite as verse, or translate</li><li>Terminal mode turns dictation into shell commands</li><li>Works with OpenAI, Anthropic, or any OpenAI-compatible provider such as OpenRouter; every prompt is editable</li></ul>\n\n<b>Keyboard</b>\n<ul><li>One tap takes you back to the keyboard you came from</li><li>Punctuation keys, accelerating backspace, send key, persistent clipboard bar</li><li>The Enter key runs the field's own action: Search, Go, Send, Next or Done</li><li>The microphone is off in password fields</li><li>Spacing around dictated text follows the text already in the field</li><li>Light, dark and automatic themes; 17 interface languages</li></ul>\n\n<b>Privacy</b>\n<ul><li>No analytics, no advertising, no tracking, no account, no servers of our own</li><li>API keys and settings stay on the device and are excluded from cloud backup</li><li>Audio is sent only to the endpoint y","categories":["Keyboard & IME","Speech Recognizer"]}