Video to text: transcribe your videos with AI

Two ways to transcribe a video

You have the video file: File mode

Upload your MP4 or MOV video directly (up to 500 MB). The audio is extracted and transcribed with timestamps. This is the most reliable method for a recorded video: a video call export, a phone video, a screen recording.

The video plays in your browser: Live mode

If you do not have the file (online video, replay, livestream), Live mode can capture your computer's audio through the browser's tab sharing and transcribe it while the video plays. Audio capture works in Chrome and Edge on a computer. Respect the rights of the video's author.

Transcribe a video file in 4 steps

1. Sign in to voqia.fr with Google (10 free minutes, no credit card).
2. Open File mode and drop your MP4 or MOV video, or an audio file if you already extracted it.
3. Turn on speaker separation (diarization) if several people talk, then start the transcription.
4. Review the timestamped text, rename the speakers, then copy it or export it to Word.

What you get

• Timestamped text, to jump back to a passage in the video quickly.
• Speaker labels (Speaker 1, Speaker 2…) that you can rename: useful for interviews and panels.
• An AI summary of the key points.
• A Word (.docx) export or one-click copy.
• Need a translation? In Live mode, the text can be translated while the video plays, into English, French, German, Spanish, Italian, Portuguese or Arabic.

What about subtitles?

Voqia gives you a timestamped transcript, not a ready-made subtitle file (SRT or VTT). The transcript is the starting point: paste it into your video editor or subtitling tool, which handles the timing on screen. The longest part of subtitling, typing what is said, is done for you.

If your video is larger than 500 MB

Long HD videos quickly go over the limit. Only the audio matters for transcription, so there are two simple fixes:

• export the audio only from your editing or video call software (MP3 or M4A), which is a much smaller file;
• re-export the video at a lower resolution: image quality has no effect on the transcript.

Languages

Voqia transcribes English, French, Spanish, German, Italian, Portuguese, Arabic, Russian and Turkish, and detects the spoken language automatically. For a video in another language, test a short extract with your free minutes first.

Getting an accurate transcript

Quality depends mostly on the sound: a voice close to the microphone, little background music and few people talking over each other give the best results. Always check names and technical terms before publishing or quoting the text.

Pricing

The first 10 minutes are free. After that, minutes are bought once, with no subscription: €4.99 for 1 hour, €9.99 for 3 hours, €24.99 for 10 hours. A one-hour video uses one hour of transcription. Minutes never expire.

Frequently asked questions