Transcribe Audio & Video to Text

We support all major audio and video formats including MP3, WAV, M4A, FLAC, OGG, MP4, MOV, AVI, MKV, WebM, and more. If your browser can play it, we can likely transcribe it.

We use state-of-the-art AI speech recognition, which achieves over 95% accuracy for clear audio in English. Accuracy may vary based on audio quality, background noise, accents, and technical terminology.

We currently support English transcription. Support for additional languages is coming soon. If you need a specific language, feel free to contact us.

There's no strict file size limit, but very large files (over 2GB) may take longer to upload. For best results, we recommend keeping files under 500MB when possible. Long recordings work fine—just ensure you have enough credits.

1 credit equals 1 minute of audio or video. Credits are calculated based on the actual duration of your file, rounded up to the nearest minute. For example, a 5:30 video uses 6 credits. Unused credits never expire.

No! Every new account gets 120 free credits (2 hours of transcription) with no credit card required. You only pay when you need more credits.

Most transcriptions complete in about 20-50% of the audio duration. A 10-minute video typically takes 2-5 minutes to transcribe. Processing time may vary based on server load and file complexity.

Yes. Your files are encrypted during upload and processing. We don't share your files or transcriptions with third parties. Files are automatically deleted from our processing servers after transcription is complete. You can delete your transcriptions from your account at any time.

You can export transcriptions in multiple formats: plain text (TXT), Markdown (MD), SubRip subtitles (SRT), WebVTT (VTT), tab-separated values (TSV), and JSON. SRT and VTT formats include timestamps, perfect for creating subtitles.

Yes! All transcriptions include word-level timestamps. You can view the transcript synced with your audio/video, and export with timestamps in SRT, VTT, or JSON formats for subtitles or further processing.

Yes, our transcription includes automatic speaker diarization. The system detects and labels different speakers (Speaker A, Speaker B, etc.) in conversations, interviews, and meetings.

If a transcription fails due to a technical issue on our end, the credits are automatically refunded to your account. For other issues, contact us and we'll work with you to find a solution.