Auto-generated captions¶
This guide will demonstrate how to enable auto-captioning for on-demand HeapStream videos to enhance accessibility and generate transcripts.
Overview¶
HeapStream utilizes OpenAI's Whisper model for automatic captioning of on-demand videos.
This feature works best with clear audio, but may struggle with excessive non-speech sounds or silence.
We recommend testing it on your typical content to assess its performance for your use case.
Enabling auto-captioning¶
- Enable auto-captioning for all videos in the
Project Settingspage. - Enable auto-captioning when uploading a video in the
Video Uploadpage. - Generate captions for an existing video in the
Video Edit -> Text Trackspage.
- Enable auto-captioning for all videos of a project in the API ⧉ "Update project settings" endpoint.
- Set the
auto_ttarray when uploading ⧉ or fetching ⧉ a video. - Generate captions for an existing video through the endpoint "Generate auto captions" in the API ⧉
FAQ¶
List of supported languages¶
Below are supported VOD auto-captioning languages and codes (note that beta languages may have lower accuracy):
| Language | Language Code | Status |
|---|---|---|
| English | en | Stable |
| Spanish | es | Stable |
| Italian | it | Stable |
| Portuguese | pt | Stable |
| German | de | Stable |
| French | fr | Stable |
| Korean | ko | Stable |
| Dutch | nl | Stable |
| Thai | th | Stable |
| Russian | ru | Stable |
| Polish | pl | Stable |
| Japanese | ja | Stable |
| Swedish | sv | Stable |
| Turkish | tr | Stable |
| Catalan | ca | Stable |
| Indonesian | id | Stable |
| Ukrainian | uk | Stable |
| Malay | ms | Stable |
| Mandarin | zh | Stable |
| Finnish | fi | Stable |
| Norwegian | no | Stable |
| Romanian | ro | Stable |
What is the cost of auto-captioning for VOD?¶
It's free.
Time needed to generate captions?¶
For English, it's about 0.2x duration of the speech. For other languages, it takes 0.5x duration.
My audio speech is in multiple languages¶
It's not recommended to use auto-captioning on content with multiple languages.
My video has multiple audio tracks (e.g. a dub or a commentary)¶
Captions are generated per audio track. By default the video's main audio track is captioned. To caption a specific alternate audio track, pass its audio_track_id to the "Generate auto captions" endpoint — each audio track gets its own captions, even when two tracks share the same language (for example a main track and a separate commentary track). Deleting an audio track also removes the captions that were generated from it.
The speech is in a language you don't support¶
Please contact us regarding any unsupported languages you need for auto-captioning.
Auto-generated captions may have mistakes¶
While automatic speech recognition has significantly improved, occasional errors may still occur.
One option is to edit the auto-generated captions:
- Download the VTT file through the API or GUI
- Correct mistakes in a text editor
- Delete the auto-generated track
- Create a new track with the edited VTT file