Local file transcription
Transcribe audio or video on the computer without uploading the file.
Yap Audio to Text
Yap Audio to Text is a free browser tool that transcribes local audio or video files into editable text and timed SRT or VTT subtitles. Whisper runs on the user’s computer, with no account or upload, subject to a 60-minute and 300 MB limit per file.
Yap Audio to Text
Yap Audio to Text converts an existing audio or video file into a transcript in the browser. It runs Whisper on the user’s computer rather than uploading the recording, and does not require an account.
Choose a supported file, wait for the browser model and transcription, then review the text and save it. Text edits affect copied text and TXT downloads; SRT and VTT subtitles use the originally recognized text and timings. Keep the tab open until the files are saved.
Key Features
Common input formats
Accepts MP3, M4A, WAV, OGG, FLAC, MP4, MOV, and WebM, up to 60 minutes and 300 MB per file.
Editable transcript
Correct recognized text and copy it or download a TXT file.
Timed subtitle export
Download SRT or VTT subtitles using the recognized text and segment timings.
Language modes
Use English mode or an Any language mode covering 99 languages with automatic detection and lower accuracy.
Browser model download
The first use downloads a Whisper model of about 80 MB, or about 165 MB with the graphics-chip path where supported.
Use Cases
Recorded interviews
Create a draft transcript of an interview and manually check names and technical terms.
Lecture notes
Convert a recorded lecture into text for review and note-taking.
Video subtitles
Produce timed subtitle files, then review and edit them in a suitable subtitle tool.
Private recording review
Work with a local recording when avoiding a file upload is important.
Pros and Cons
Pros
- Free and no account required.
- Audio and transcripts stay in the current browser tab.
- Provides editable text and SRT/VTT exports.
Cons
- Each file is limited to 60 minutes and 300 MB.
- The small browser model can struggle with names, overlapping speech, music, and noise; it does not label speakers.
- Editing the text box does not update SRT/VTT subtitle text. Save outputs before closing the tab.
FAQ
Is it free and private?
The official page presents this file-transcription tool as free without sign-up. The file and transcript stay in the tab and are not uploaded; the browser first downloads a model.
What are the limits?
Each input file may be up to 60 minutes and 300 MB. This is not an unlimited-length transcription service.
Which outputs can I save?
Copy or download edited text as TXT. Download SRT or VTT subtitles with the recognized text and original timings; text-box edits do not alter those subtitle files.
Does it identify speakers?
No. The page explicitly says the browser tool does not tell speakers apart.
Is it the same as Yap desktop dictation?
No. This page transcribes existing files in a browser. The separate Yap desktop app recognizes live speech into other applications and has its own trial and pricing.
Quick Facts
- Product type
- Browser file transcription
- Access
- Free; no account
- Per-file limit
- 60 minutes and 300 MB
- Outputs
- TXT, SRT, VTT
- Processing
- Local Whisper; initial model download
- Developer
- O-mega Enterprise Inc.
Yap Audio to Text Alternatives
CAKIE
CAKIE is a Mac app for recording your screen and voice for an AI agent, with transcripts, screenshot highlights, and easy prompt copying.
SpeakoFlow
SpeakoFlow is a free, open-source desktop voice-to-text app for Windows, macOS, and Linux. Dictate into any app, use Flow, cleanup, translation, and a screen-aware assistant.
QuickQuill
QuickQuill is a local-first macOS dictation and transcription app to record meetings, summarize audio, and export notes without the cloud.
Zen Whisper
Zen Whisper is a local-first dictation and transcription app for Apple Silicon Macs on macOS 14+. Dictate into most Mac text fields and transcribe media or supported public links across 110 languages.
Speech to Text Converter
Speech to Text Converter is a browser-based transcription tool for live dictation and uploaded audio or video files. Free for short tasks, Pro offers unlimited transcription, AI summaries, translation, speaker ID, and advanced exports.
Flunkey
Flunkey is a voice-first productivity layer for Windows that turns speech into text, AI outputs, and remembered context without leaving your app.