← OGS Apps

🎙️ Speech to Text

⏳ No model loaded

🌙 Moonshine Base ⓘ

Drop an audio file here or click to browse

Supports MP3, WAV, OGG, M4A, WebM

Powered by 🤗 Whisper & Transformers.js · 🔒 100% Private ⓘ

OGS Apps · Client-side AI speech recognition

Info

Welcome to Speech to Text 👋

Choose an AI model size, download it, and start transcribing — entirely in your browser. No data is sent to any server.

Tiny (40MB) — Fastest, good for quick notes Default
Base (75MB) — Balanced speed and accuracy
Small (250MB) — Most accurate, slower

Record mode — Click mic, speak, click again to stop. Most reliable.
Real-time mode — Streams audio in chunks, transcribes live. Experimental.
Upload mode — Upload an audio file (MP3, WAV, etc.) for transcription.