Improving live caption quality

There are several ways to improve the quality of live captions and translations in Timbra.

If you're using an HLS stream as your source, increasing the HLS segment size gives Timbra more context to produce higher quality captions.

We recommend using a segment size of 10 seconds. The minimum supported segment size is 6 seconds.

For Brightcove streams, see How to increase the HLS segment size in Brightcove.

Language profiles allow you to control how captions are generated. For example, you can configure:

These settings can also be configured on a per-language basis.

Custom dictionaries bias speech recognition towards specific words and phrases.

For live events, we recommend including:

This helps improve transcription accuracy, particularly for specialist vocabulary.

Termbases influence how words and phrases are translated, helping to maintain consistent terminology across languages.

They're particularly useful for:

From Global translation settings, you can configure features such as:

If you need different settings for individual languages, click the pencil icon next to the language to open its language-specific settings. From there, you can also attach Substitution dictionaries.

Amazon Translate is one of the machine translation providers supported by Timbra. When used, you can also take advantage of Amazon Translate-specific features.