{"package_name":"com.antivocale.app","name":"Anti-Vocale","summary":"Offline transcription of voice messages and recorded calls, on-device","category":"Speech Recognizer","icon_url":"/api/icon/com.antivocale.app","latest_version_code":442,"latest_version_name":"1.13.0","apk_url":"/api/apk/com.antivocale.app","apk_size":36418153,"apk_sha256":"dbf662819f7ee920fba403b7a8763508350b852025316aee08b98014d8420e7b","source_kind":"fdroid-repo","repo_slug":"fdroid-main","last_updated":1790132417,"release_timestamp":1790107369,"description":"Anti-Vocale transcribes voice messages from WhatsApp, Telegram, and other messaging apps directly on your Android device. All processing happens on-device: your audio never leaves your phone. It works on recorded calls and meetings too: recordings of any length are split and stitched automatically (up to two hours on the streaming path), a failed run keeps the transcript it produced, and long transcripts can be exported as subtitles (SRT, VTT) or timestamped text, with sentence-level timing on streaming models.\n\nBUILT-IN MODELS\n\n- Parakeet TDT (recommended): fast, 25 European languages. Two variants: high-quality (862MB) or compact (464MB)\n- Whisper Turbo: 99 languages, balanced speed and quality\n- Whisper Distil Italian: best Italian quality, tuned for voice messages\n- Whisper Medium / Small: more accuracy or smaller download\n- Nemotron 3.5 streaming: text appears in real time while it decodes, 45 languages\n- Qwen3-ASR: compact, 59 languages\n- GigaAM v3: Russian, very small and fast\n- Gemma 4 / 3n (LiteRT): multimodal AI with customizable prompts\n\nBRING YOUR OWN MODELS\n\nImport custom transcription models from a folder on your phone or from a link: Whisper fine-tunes, CTC models, SenseVoice and other sherpa-onnx architectures. Files are integrity-checked on import, split-file models are supported, and every imported model gets its own share target. Ideal for languages the built-in models don't cover.\n\nFEATURES\n\n- Share voice messages from any app via the Android share sheet\n- Smart notifications: one-tap copy, share back, page through long transcripts without opening the app\n- Auto-copy to clipboard and auto-save transcripts to a folder you pick (Drive, Syncthing, ...)\n- Video file transcription (audio track extracted)\n- Real-time progressive text with streaming models\n- Per-app notification preferences\n- Transcription log with search and swipe actions\n- Silence stripping and parallel chunk processing for speed\n- Neural acceleration (NNAPI) on supported devices, wit","categories":["Speech Recognizer"]}