Find out what a video is about. AI tags it with standard IAB ad categories and topics, useful for sponsors, playlists and content libraries.
Free for recordings up to 1 hour and 1 GB. Longer files need a paid plan.
How It Works
Drop an audio or video file — MP4, MOV, MP3, WAV, M4A and more. The language is detected automatically.
AssemblyAI transcribes every word with exact timings — usually a fraction of the recording's length.
Read the result on the page, then download it along with the full transcript.
The Video Topic Detector is a free online tool from ShortsHero: ad categories for any video. AssemblyAI speech recognition does the work — a 5-minute recording usually comes back in under 30 seconds. It is free for files up to 1 hour with no watermark; longer recordings need a paid plan.
Free transcription covers files up to 1 hour. If your recording is longer, a paid plan lifts the limit — or trim it into parts and run each one.
Why Use This Tool
Every word carries its start and end time, so subtitles line up with the speech.
The formats YouTube, Premiere, Resolve, CapCut and every major player accept.
Filter the transcript on the page to find any word and jump to its timestamp.
Full recordings, not a one-minute sample. Paid plans lift the length limit.
The spoken language is detected automatically.
Use the files anywhere — the transcript and subtitles are yours.
Yes. Files up to 1 hour long are free, with no watermark and no account needed. Recordings longer than 1 hour need a paid ShortsHero plan.
MP4, MOV, WebM, MKV, MP3, WAV, M4A, AAC, OGG, FLAC and most other audio and video formats, up to 1 GB. For a long video, uploading just the audio is faster.
Yes. Download the SRT and open it in our free online SRT editor, or in any video editor, to fix a word or a timing.
Usually well under the length of the recording — a 10-minute file is typically done in about a minute.
ShortsHero turns long videos into short vertical clips with AI moment detection, face tracking and animated captions — and has free tools for subtitles, transcripts and video formats.
The same transcription powers ShortsHero's clip maker: it finds the strongest moments, reframes them to vertical and adds word-by-word captions in 36 styles.
Try the clip maker freeFree to start · No credit card required
Keep Going
Check a video for brand-safety risks before a sponsor sees it. Flags violence, drugs, hate speech and other sensitive talk with timestamps and severity.
Get a true verbatim transcript that keeps every um, uh, stutter and repeat. Needed for legal, research and linguistics work where exact speech matters.
Get a clean verbatim transcript: fillers, stutters and false starts removed so it reads well, while the meaning stays exactly what the speaker said.
Turn Speaker A and B into real names. Give the guest list or roles, and AI works out who is who from context, then labels the whole transcript.
See how much each person talked in a call or podcast. Get talk-time percentages, longest monologues and interruptions, with a timeline per speaker.
Turn a lecture or YouTube video into flashcards. AI writes question-and-answer cards from what was said and exports them for Anki or Quizlet.