> ## 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.

# Audio Models

> Liquid's LFM audio models are among the smallest fully interleaved audio/text-in, audio/text-out models with a complete reasoning backbone — eliminating the need to combine separate TTS/ASR encoders with a standalone language model.

<div className="use-cases" style={{marginTop: '-0.5rem'}}>
  <CardGroup cols={2}>
    <Card title="Text-to-Speech" icon="volume-high">
      Natural speech synthesis with multiple voice styles and personalities.
    </Card>

    <Card title="Speech Recognition" icon="ear-listen">
      Multilingual automatic speech recognition and transcription.
    </Card>

    <Card title="Audio-to-Audio" icon="waveform">
      Fully interleaved voice chat with reasoning and generation in one model.
    </Card>

    <Card title="Audio Function Calling" icon="bolt">
      Voice-driven tool use, agent workflows, and API orchestration.
    </Card>
  </CardGroup>
</div>

<h2>LFM2.5 Models   <Badge shape="rounded" icon="circle-check" color="green" size="lg">Latest release</Badge></h2>

<Info>LFM2.5-Audio adds a custom LFM-based audio detokenizer, llama.cpp-compatible GGUFs for CPU inference, and improved ASR and TTS performance over LFM2-Audio.</Info>

<CardGroup cols={2}>
  <Card title="LFM2.5-Audio-1.5B" href="/lfm/models/lfm25-audio-1.5b">
    1.5B · <Badge shape="pill" color="green">Recommended</Badge>

    Best audio model for most use cases. Fast, accurate, and CPU-friendly.
  </Card>
</CardGroup>

## LFM2 Models

<CardGroup cols={2}>
  <Card title="LFM2-Audio-1.5B" href="/lfm/models/lfm2-audio-1.5b">
    1.5B · <Badge shape="pill" color="gray">Deprecated</Badge>

    Use the new LFM2.5-Audio-1.5B checkpoint instead.
  </Card>
</CardGroup>

## Examples

Explore practical implementations using audio models:

<CardGroup cols={2}>
  <Card title="Real-Time Audio Transcription CLI" href="/examples/laptop-examples/audio-to-text-in-real-time">
    Transcribe audio files locally in real-time using LFM2-Audio-1.5B with llama.cpp for 100% private, on-device processing.

    **Platform:** Desktop · **Uses:** LFM2-Audio-1.5B
  </Card>

  <Card title="Browser Audio Demo with WebGPU" href="/examples/web/audio-webgpu-demo">
    Run ASR, TTS, and interleaved conversations entirely in-browser using LFM2.5-Audio-1.5B with WebGPU acceleration.

    **Platform:** Web · **Uses:** LFM2.5-Audio-1.5B
  </Card>
</CardGroup>

<Panel>
  * [Liquid Playground](https://playground.liquid.ai/chat?model=cmk0wefde000204jp2knb2qr8)
  * [HuggingFace Collections](https://huggingface.co/LiquidAI/collections)
  * [OpenRouter API](https://openrouter.ai/liquid)
  * [LEAP Model Library](https://leap.liquid.ai/models)
</Panel>