Overview
Video reviews are some of your most persuasive content, but many shoppers browse with the sound off, and moderators rarely have time to watch every clip. Okendo transcribes every video review automatically, so shoppers get subtitles and a transcript on your storefront, and you can scan the transcript when you moderate. Review images also get AI-generated alt text.
How video transcription works
When a customer submits a video review, Okendo automatically processes the audio and generates a text transcription using AI speech-to-text. Transcription supports 100+ languages, and the entire process runs in the background: no configuration or action is needed from you or your reviewers.
Once generated, the transcription is used to display inline subtitles on your storefront. The full transcript also appears in the storefront media modal, and in the admin moderation panel so you can check it before publishing a review.
Video reviews submitted after October 25, 2025 are automatically transcribed. Videos submitted before this date are not retroactively transcribed.
Subtitles and transcripts on the storefront
When a shopper expands a video review in the reviews widget, the media modal displays inline subtitles directly on the video player during playback. The full transcript text is also shown alongside the video in the modal panel, so shoppers can read along in real time or review the full transcript at their own pace. Shoppers can also click on the timestamps to jump directly to that point in the video.
Transcripts in the admin moderation panel
When you open a video review in the media moderation modal within the Okendo admin, the full transcript is displayed alongside the video. You can quickly scan or click on the timestamps to review the spoken content of a video without needing to watch the full clip, particularly useful if your store receives a high volume of video reviews.
Image alt text in the admin moderation panel
The media moderation modal in the Okendo admin displays an AI-generated alt text description for review images. This gives you a quick text-based summary of the image content, making it easier to assess submissions during moderation.
FAQs & Troubleshooting
Q: Do I need to enable video transcription?
A: No. Transcription is automatic for all new video review submissions. There are no settings to configure.
Q: Will existing video reviews be transcribed?
A: Video reviews submitted after October 25, 2025 are transcribed automatically. Videos submitted before this date aren't transcribed retroactively.
Q: What languages are supported?
A: Transcription supports 100+ languages, powered by AI speech-to-text. This includes major global languages such as English, Spanish, French, German, Portuguese, Japanese, Korean, Chinese, Arabic, Hindi, and many more. Accuracy may vary by language, accent, and audio quality.
Q: How accurate is the transcription?
A: The AI-generated transcription is generally high quality, but may occasionally contain inaccuracies, particularly with strong accents, background noise, or niche product terminology.
Q: Can I edit or remove a transcript?
A: Transcripts can't be edited at this time. If you reject or delete a video review through moderation, its transcript is deleted too.
Q: Do subtitles show automatically on the storefront?
A: Yes. When a shopper plays a video in the reviews widget media modal, inline subtitles are displayed automatically on the video player.
Q: Does this affect my store's performance?
A: No. Transcription runs asynchronously on Okendo's infrastructure, with no impact on storefront load times or performance.
Q: How is the image alt text generated?
A: Alt text for review images is generated using AI image analysis. It gives a brief text description of the image, displayed in the admin moderation modal to help moderators quickly assess submissions.



