Audio Transcription
- Created by
- Renato Passos, Eng. de Software
- Reviewed by
- Renato Passos, Eng. de Software
Last updated: Apr 18, 2026
About this tool
Transcribe audio to text with AI. Accepts MP3, WAV, M4A, OGG, FLAC, WEBM, and AAC up to 24MB. Ideal for interviews, classes, meetings, and podcasts.
Privacy: your file is streamed directly to the AI provider, transcribed, and discarded. Nothing is stored on our servers, database, or cloud storage. Zero persistence.
Frequently asked questions
Is the audio stored after transcription?
No. The file is processed in memory, sent to the AI provider (Groq Whisper), and discarded at the end of the request. Not a single byte of audio touches our disk, database, or cloud storage.
What is the size limit?
24MB per file. For larger audio, split the file into chunks or compress it first (you can use our Video Compressor with audio extraction).
Which formats are supported?
MP3, WAV, M4A, OGG, FLAC, WEBM, AAC. MP4 and WEBM videos are also accepted — the audio track is extracted automatically.
Does the transcript include punctuation?
Yes. The Whisper-large-v3 model from Groq adds punctuation and capitalization based on context. Accuracy is high in its natively supported languages (English, Portuguese, Spanish, etc.).
How many transcriptions can I do per hour?
10 transcriptions per hour per IP, free. If you need more volume, we will soon launch a Pro plan with a larger quota.