> ## 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.

# LFM2.5-Audio-1.5B-JP

> 1.5B Japanese-focused audio/text model for TTS, ASR, and voice chat

<a href="/lfm/models/audio-models" className="back-button">← Back to Audio Models</a>

LFM2.5-Audio-1.5B-JP is the Japanese-focused variant of LFM2.5-Audio-1.5B. It uses the same audio/text architecture and runtime path as the English model, with Japanese-focused ASR, TTS, and interleaved voice chat behavior.

<div style={{display: 'flex', gap: '0.5rem', margin: '0.5rem 0 1.5rem 0'}}>
  <a href="https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B-JP" style={{padding: '0.35rem 0.7rem', borderRadius: '4px', fontSize: '0.85rem', fontWeight: 600, textDecoration: 'none', backgroundColor: '#fbbf24'}}><span style={{color: '#000'}}>HF</span></a>
  <a href="https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B-JP-GGUF" style={{padding: '0.35rem 0.7rem', borderRadius: '4px', fontSize: '0.85rem', fontWeight: 600, textDecoration: 'none', backgroundColor: '#60a5fa'}}><span style={{color: '#000'}}>GGUF</span></a>
</div>

## Specifications

| Property           | Value                               |
| ------------------ | ----------------------------------- |
| Parameters         | 1.5B (1.2B LM + 115M audio encoder) |
| Context Length     | 32K tokens                          |
| Audio Output       | 24kHz                               |
| Supported Language | Japanese                            |

<div className="use-cases">
  <CardGroup cols={3}>
    <Card title="Japanese TTS" icon="volume-high">
      Natural Japanese speech synthesis
    </Card>

    <Card title="Japanese ASR" icon="ear-listen">
      Japanese speech recognition
    </Card>

    <Card title="Voice Chat" icon="waveform">
      Interleaved Japanese audio/text
    </Card>
  </CardGroup>
</div>

## Quick Start

<Tabs>
  <Tab title="liquid-audio">
    **Install:**

    ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
    pip install liquid-audio
    pip install "liquid-audio[demo]"  # optional, for demo dependencies
    pip install flash-attn --no-build-isolation  # optional, for flash attention 2
    ```

    **Multi-Turn Chat:**

    ```python theme={"theme":{"light":"github-light","dark":"github-dark"}}
    import torch
    import soundfile as sf
    from liquid_audio import LFM2AudioModel, LFM2AudioProcessor, ChatState, LFMModality

    HF_REPO = "LiquidAI/LFM2.5-Audio-1.5B-JP"
    processor = LFM2AudioProcessor.from_pretrained(HF_REPO).eval()
    model = LFM2AudioModel.from_pretrained(HF_REPO).eval()

    chat = ChatState(processor)
    chat.new_turn("system")
    chat.add_text("Respond with interleaved text and audio.")
    chat.end_turn()

    chat.new_turn("user")
    wav, sampling_rate = sf.read("question_jp.wav", dtype="float32")
    wav = torch.from_numpy(wav).unsqueeze(0)
    chat.add_audio(wav, sampling_rate)
    chat.end_turn()

    chat.new_turn("assistant")

    text_out, audio_out, modality_out = [], [], []
    for t in model.generate_interleaved(**chat, max_new_tokens=512, audio_temperature=1.0, audio_top_k=4):
        if t.numel() == 1:
            print(processor.text.decode(t), end="", flush=True)
            text_out.append(t)
            modality_out.append(LFMModality.TEXT)
        else:
            audio_out.append(t)
            modality_out.append(LFMModality.AUDIO_OUT)

    audio_codes = torch.stack(audio_out[:-1], 1).unsqueeze(0)
    waveform = processor.decode(audio_codes)
    sf.write("answer_jp.wav", waveform.cpu()[0], 24_000)
    ```

    **Japanese ASR:**

    ```python theme={"theme":{"light":"github-light","dark":"github-dark"}}
    chat = ChatState(processor)
    chat.new_turn("system")
    chat.add_text("Perform ASR in japanese.")
    chat.end_turn()
    ```

    **Japanese TTS:**

    ```python theme={"theme":{"light":"github-light","dark":"github-dark"}}
    chat = ChatState(processor)
    chat.new_turn("system")
    chat.add_text("Perform TTS in japanese.")
    chat.end_turn()
    ```
  </Tab>

  <Tab title="llama.cpp">
    **Setup:**

    ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
    export CKPT=/path/to/LFM2.5-Audio-1.5B-JP-GGUF
    export INPUT_WAV=/path/to/input.wav
    export OUTPUT_WAV=/path/to/output.wav
    ```

    **ASR (Audio to Text):**

    ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
    ./llama-liquid-audio-cli -m $CKPT/LFM2.5-Audio-1.5B-JP-Q4_0.gguf \
      -mm $CKPT/mmproj-LFM2.5-Audio-1.5B-JP-Q4_0.gguf \
      -mv $CKPT/vocoder-LFM2.5-Audio-1.5B-JP-Q4_0.gguf \
      --tts-speaker-file $CKPT/tokenizer-LFM2.5-Audio-1.5B-JP-Q4_0.gguf \
      -sys "Perform ASR in japanese." --audio $INPUT_WAV
    ```

    **TTS (Text to Audio):**

    ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
    ./llama-liquid-audio-cli -m $CKPT/LFM2.5-Audio-1.5B-JP-Q4_0.gguf \
      -mm $CKPT/mmproj-LFM2.5-Audio-1.5B-JP-Q4_0.gguf \
      -mv $CKPT/vocoder-LFM2.5-Audio-1.5B-JP-Q4_0.gguf \
      --tts-speaker-file $CKPT/tokenizer-LFM2.5-Audio-1.5B-JP-Q4_0.gguf \
      -sys "Perform TTS in japanese." -p "こんにちは。今日はどのようなご用件でしょうか。" --output $OUTPUT_WAV
    ```

    **Interleaved Mode:**

    ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
    ./llama-liquid-audio-cli -m $CKPT/LFM2.5-Audio-1.5B-JP-Q4_0.gguf \
      -mm $CKPT/mmproj-LFM2.5-Audio-1.5B-JP-Q4_0.gguf \
      -mv $CKPT/vocoder-LFM2.5-Audio-1.5B-JP-Q4_0.gguf \
      --tts-speaker-file $CKPT/tokenizer-LFM2.5-Audio-1.5B-JP-Q4_0.gguf \
      -sys "Respond with interleaved text and audio." \
      --audio $INPUT_WAV --output $OUTPUT_WAV
    ```

    <Info>
      Use the same llama.cpp audio runners as LFM2.5-Audio-1.5B.
    </Info>
  </Tab>
</Tabs>