---
title: "Audio & video upload in chat | Langdock Changelog"
description: "We're excited to announce that you can now work with audio and video files in the chat. Upload your recordings (up to 200MB) and our system will automatically…"
url: "https://langdock.com/changelog/transcribe-audio"
language: "en"
---

[Changelog](https://langdock.com/changelog)

Jan 26, 2025

# Audio & video upload in chat

We're excited to announce that you can now work with audio and video files in the chat.

Upload your recordings (up to 200MB) and our system will automatically transcribe them, allowing you to have natural conversations about the content.

You can work with all common formats including MP4, MP3, WAV, and MPEG files. Whether you need to review a team meeting, analyze a client call, or process a voice memo, simply upload your file and start asking questions about its content.

Improvements

- **Llama 3.3 model**: We added the newer Llama 3.3 70B model to the platform
- **OpenAI o1**: We added the o1 model from OpenAI to the platform. However, it is only available as a global deployment, which means that servers could potentially be outside of the EU. The model is turned off by default, but admins can activate it in the settings.
- **Amazon Nova models**: We added the Nova models from Amazon in the model settings. However, they are only available in the US at this point.
- **Gemini as backbone model**: Admins can set up Gemini models as a backbone model now. The backbone model defines tasks in the background for some models.

[OlderWeb search mode](https://langdock.com/changelog/web-search-mode) [NewerDeepSeek-R1](https://langdock.com/changelog/deepseek-r1)
