# OpenAI Whisper Speech-to-Text Enhancements

**URL:** <https://community.wowza.com/t/openai-whisper-speech-to-text-enhancements/102765>\
**Category:** Wowza Streaming Engine\
**Created:** [October 21, 2025, 10:58am UTC](https://community.wowza.com/t/openai-whisper-speech-to-text-enhancements/102765 "2025-10-21T10:58:28Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Umair\_Siddiqi](https://avatars.discourse-cdn.com/v4/letter/u/e8c25b/32.png) [@Umair\_Siddiqi](https://community.wowza.com/u/Umair_Siddiqi)\
**Post date:** [October 21, 2025, 10:58am UTC](https://community.wowza.com/t/openai-whisper-speech-to-text-enhancements/102765/1 "2025-10-21T10:58:28Z")

</div>

Hello All,

We’ve recently updated our documentation and GitHub resources for the **OpenAI Whisper speech-to-text module**. The latest improvements include:

- **Translation support** : learn how to enable Whisper’s translation capabilities.

- **GPU processing support** : details on how to configure and leverage GPU acceleration for improved performance.

You can review the updated resources here:

- [Convert Speech to Text to Generate Live Stream Captions with OpenAI Whisper](https://www.wowza.com/docs/convert-speech-to-text-to-generate-live-stream-captions-with-openai-whisper)

- [GitHub: wse-plugin-caption-handlers](https://github.com/WowzaMediaSystems/wse-plugin-caption-handlers)

- [GitHub: Whisper Streaming README](https://github.com/WowzaMediaSystems/whisper_streaming/blob/main/README.md)

These updates are not tied to a specific Wowza Streaming Engine release but provide additional flexibility and functionality for users implementing live captioning workflows.
