Files are read in your browser. Scanned PDFs have no text layer; use the OCR tab for those.
ދިވެހި
English
Meeting transcription
00:00
Voice dictation
Text to speech
Uses your device voices. Dhivehi voices are rarely installed; connect a TTS API for native output.
Voice cloning · coming soon
- Record or upload 30–60 seconds of clean speech.
- Confirm the voice is yours or you have written consent.
- Train, then test with a sample sentence.
Not available yet: needs a voice-cloning service connected on the server.
Uses your configured vision-capable model (e.g. Gemini). Always proofread Thaana output.
Prices are placeholders. Edit the PLANS array in the script.