Video to Text User Guide | Upload, Transcribe & Export
Learn how to use Video to Text from upload to export, including file limits, language options, and transcript downloads.
Video to Text turns audio and video into transcripts you can download and reuse. This guide walks through the current workflow from sign-in to export.
1. Sign in first
You need an account before starting a transcription. After you sign in, the app can check your available minutes and attach the result to your account session.
New users receive 30 free minutes. If your remaining minutes are not enough for the file you selected, the app asks you to top up before processing starts.
2. Upload a supported file
Choose the audio or video file you want to transcribe.
Video to Text currently accepts:
- Audio:
.aac,.flac,.m4a,.mp3,.oga,.ogg,.opus,.wav - Video:
.mp4,.m4v,.webm
The current upload limits are:
- maximum file size: 5 GB
- maximum media duration: under 10 hours
If the file is too large or too long, the app stops the process before transcription begins.
3. Choose language settings
Before you submit the file, choose the language option that best matches the recording:
- select a specific language if you already know it
- use automatic language detection if you are not sure
- use multilingual detection if the speakers switch between languages
This is useful for interviews, international meetings, lessons, podcasts, and mixed-language recordings.
4. Turn on speaker labels if needed
If your recording includes more than one speaker, you can enable speaker labels. This helps structure the transcript and makes exported files easier to review.
Speaker labels are especially helpful for:
- meetings
- interviews
- panel discussions
- classroom recordings
5. Start transcription
After upload, the app begins transcription. Processing time depends on file size, upload speed, media duration, and audio clarity.
The product is built for fast turnaround, and most files complete quickly, but longer uploads can still take more time because the file must be uploaded before transcription can finish.
6. Export the result
When the transcript is ready, Video to Text takes you to the export page. You can export the result as:
csvsrtvtttxt
Use srt or vtt for subtitles, csv for structured review, and txt for plain text editing.
Practical tips
- Upload the cleanest file you have
- Choose the correct language option when possible
- Turn on speaker labels for multi-speaker content
- Export your result promptly instead of treating the service as long-term storage