> ## Documentation Index
> Fetch the complete documentation index at: https://docs.liquid.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Omni Models

> Liquid's LFM omni models bring vision, audio, and language together in a single model that can see, listen, and talk back, replacing separate ASR, vision-language, LLM, and TTS models on-device.

> **Spoken Visual Q\&A**
>
> Ask questions about images or real-world scenes using speech, and receive answers in text, speech, or both.

> **Audio-Visual Video**
>
> Reason about both what is happening on screen and what is being said or heard.

> **Speech & Voice Chat**
>
> Speech recognition, speech synthesis, translation, and interleaved voice chat.

> **Multimodal Tool Calling**
>
> Tool calls from visual context and spoken instructions to control apps and interfaces.

## LFM3 Models   Latest release

> [!NOTE]
>
> LFM3-Omni is Liquid AI's first omni model. It understands text, images, video, and audio, and answers in text, speech, or interleaved text and speech, while retaining the core capabilities of the standalone LFM3 models.

> **[LFM3-Omni-2B](https://docs.liquid.ai/lfm/models/lfm3-omni-2b)**
>
> 2B · Recommended
>
> Any input, text or speech output, in one on-device model.

## Guides

Learn how to use these models in your application:

> **[Omni Capabilities](https://docs.liquid.ai/lfm/key-concepts/omni-capabilities.md)**
>
> Speech, images, video with its soundtrack, audio understanding, and tool calling in one model.

* [Liquid Playground](https://playground.liquid.ai/chat?model=cmk0wefde000204jp2knb2qr8)
* [Hugging Face Collections](https://huggingface.co/LiquidAI/collections)
* [OpenRouter API](https://openrouter.ai/liquid)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.