语音转文字 — This tool transcribes audio to text using a small AI model that runs in your browser. The audio and the model never leave your device.
Runs entirely on your device. The audio and the model stay on your device — nothing is uploaded. The first run downloads a small local model (~40 MB); after that, transcription works offline.
Was 语音转文字 useful?
语音转文字是什么?
This tool transcribes audio to text using a small AI model that runs in your browser. The audio and the model never leave your device.
The first run downloads the model (~40 MB). After that, transcription works offline. You can upload an audio file or record from your microphone.
Output is shown as text with timestamps. You can copy the text, download as .txt, or download as .srt subtitles (compatible with YouTube, VLC, and most video editors).
Everything — the audio, the model, and the result — stays on your device. There is no upload, no account, and no analytics on the audio itself.
使用方法
-
Pick an audio source
Choose an audio file (mp3, m4a, wav, webm, ogg) or click Record to capture from your microphone.
-
Download the model on first use
The first run downloads a small local model (~40 MB). After that, transcription works offline.
-
Click Transcribe
Inference is local. A one-minute clip typically finishes in a few seconds on a modern laptop. The result appears below with timestamps.
-
Copy or download
Use Copy for plain text, or download as .txt or .srt. The .srt format works with most video editors and YouTube for subtitles.
常见问题
相关指南
The Uttir API Is Live
The Uttir API is live: 28 operations in 8 families, prepaid points, scoped keys, a free tier. What shipped, what it costs, your first call.
5 Free Local AI Tools That Run in Your Browser (No Upload, No Signup)
A practical tour of Uttir's new AI tools category: text summarization, sentiment analysis, text similarity, audio transcription, and background removal — all running on a small model inside your browser. Nothing leaves your device.
相关工具
Last reviewed: 2026-11-21