Choose Auto-detect or select one of 38 audio language options. This setting controls the expected spoken language; it does not change the website interface language.

ScribVoice requests speaker labels when supported. Labels depend on the recording and may be missing when voices are unclear or overlap. With Auto-detect, a low-confidence result may offer one free retry after you choose the spoken language.

Yes. Completed transcripts can be exported as SRT or VTT subtitles, as well as TXT or DOCX documents.

Yes. Verified video containers include MP4, M4V, MOV, WEBM, MKV, AVI, FLV, M2TS, MTS, TS, 3GP, 3G2 and MPEGTS. ScribVoice transcribes the audio track; video preview is not available in the workspace.

WhatsApp voice messages use SILK audio, which is not accepted directly. Export or convert the message to MP3 or WAV first.

Yes. Upload a supported meeting recording to get editable segments with timestamps. Speaker labels may help distinguish voices; review names and technical terms before sharing.

Yes. Edit or delete transcript segments in the workspace, then choose Save changes. Your saved edits are available when you return to the transcript.

Yes. Your recordings and transcripts are private to your account and are never shown to other users. You can delete any file at any time, and it is removed from storage immediately.