Transcription
Audio to Text with Timestamps
Upload an audio or video file and receive an accurate, timestamped transcript. Choose sentence, paragraph, or word-level grouping and export as TXT, SRT, VTT, or JSON.
Transcription Output
No transcription results yet
Upload an audio or video file and click Transcribe Audio. Your timestamped transcript and export controls will appear here.
Transcription FAQs
Common questions about Konthora's audio transcription tool.
What is the maximum upload file size?
The maximum file size per upload is 100 MB. For longer recordings, files must also be within a 10-minute duration limit.
Which file formats are supported for transcription?
Konthora accepts MP3, WAV, M4A, AAC, MP4, WebM, and MOV files. Video files are processed for their audio track only.
Which languages are supported?
Konthora currently transcribes English-language audio. Selecting "Auto Detect" will also process the audio as English. Additional language support is planned for a future release.
How accurate are the timestamps?
Timestamps are generated by Whisper, a production-grade speech recognition model. You can choose sentence-level, paragraph-level, or word-level timestamp grouping for your use case.
What export formats are available?
You can export your transcript as plain TXT, SRT subtitle format, WebVTT caption format, or structured JSON containing all segments and word-level timing data.
Are uploaded files stored permanently?
No. Uploaded media files and generated transcripts are automatically deleted after 60 minutes. Nothing is retained beyond that window.