Voxcribe

Voxcribe is an online video-to-text and audio-to-text tool that runs in your browser. Drop an MP4, MOV, WEBM, MKV or AVI video or an MP3, M4A, WAV, AAC, OGG or FLAC file; Voxcribe extracts the audio locally so the video is never uploaded, then transcribes it with automatic language detection. Every line is timestamped - click a line to play from that moment, fix names in place, and export a free TXT transcript. Paid plans add SRT/VTT and DOCX. Free: first file up to 10 minutes with no account.