Audio to Text
Upload an audio file and get an accurate AI-generated transcript in seconds. Supports MP3, WAV, M4A, WEBM, and more. Download as TXT, DOCX, SRT, or JSON.
Drop your audio file here
or click to browse
MP3 · WAV · M4A · WEBM · OGG · MP4 · Max 5 MB
Transcribing your audio…
This may take up to 30 seconds for longer files
Download transcript as:
How it works
1. Upload your audio
Drag and drop or browse for an MP3, WAV, M4A, WEBM, or OGG file up to 5 MB.
2. AI transcribes it
Powered by OpenAI Whisper — one of the most accurate speech-to-text models available, supporting 90+ languages.
3. Download your transcript
Save as plain TXT, editable DOCX, subtitle SRT (with timestamps), or raw JSON.
Supported audio formats
Max file size: 5 MB · Auto language detection across 90+ languages
Frequently asked questions
MP3, WAV, M4A, WEBM, OGG, MPEG, MPGA, and MP4. The file must be 5 MB or smaller.
The underlying model (OpenAI Whisper) supports over 90 languages and auto-detects the language from the audio automatically.
SRT (SubRip Subtitle) is a standard subtitle file with timestamps. It's ideal for adding captions to videos in YouTube, Premiere Pro, DaVinci Resolve, and most other editing tools.
No. Your audio is sent directly to the transcription API and is not saved to disk on our servers. Once you receive your transcript, the file is discarded.