Files
skills/public/hanzo-koe.html
zeekayandHanzo Dev 9e10c1c10e Each llms index points at the other two
hanzoskills.com/llms.txt now opens with the install line, the API
reference index and the company index, so an agent that lands on any
one of the three can find the rest.

robots.txt claimed 537 documents while llms.txt counts 920. The number
is gone from robots.txt; llms.txt derives it.

public/ is regenerated from scripts/site.py, which it had fallen
behind: the copy-prompt menu and agent bar were in the generator and
not in the committed pages. tests/site.mjs passes against the result.

Co-authored-by: Hanzo Dev <[email protected]>
2026-09-11 00:27:59 -07:00

351 lines
21 KiB
HTML

<!doctype html>
<html lang="en"><head>
<meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
<title>hanzo-koe</title>
<meta name="color-scheme" content="dark">
<style>
/* Committed to one visual world: a dark instrument panel. No light variant —
the dot field and the hairline rules only read on black, and a naive
inversion would wash both out. Every colour is painted explicitly so the page
never borrows a host background. */
@font-face{font-family:'Zen';src:url('/fonts/Zen-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
@font-face{font-family:'Zen';src:url('/fonts/Zen-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
@font-face{font-family:'Zen Pixel Square';src:url('/fonts/ZenPixel-Square.woff2') format('woff2');font-style:normal;font-display:swap}
:root{
--ink:#f4f4f2; --soft:#9c9c98; --faint:#6a6a66; --ground:#000; --panel:#0a0a0a;
--line:#232323; --line-hi:#3a3a3a; --accent:#f4f4f2;
--font-zen-sans:'Zen',-apple-system,BlinkMacSystemFont,"Segoe UI",Helvetica,Arial,sans-serif;
--font-zen-mono:'Zen Mono',ui-monospace,"SF Mono",SFMono-Regular,Menlo,Consolas,monospace;
--font-zen-pixel-square:'Zen Pixel Square',monospace;
--mono:var(--font-zen-mono);
--sans:var(--font-zen-sans);
/* Controls are pills and surfaces are soft, as on hanzo.ai. */
--r:999px; --r-soft:14px;
}
*{box-sizing:border-box}
html{-webkit-text-size-adjust:100%}
body{margin:0;background:var(--ground);color:var(--ink);font-family:var(--sans);
font-size:16px;line-height:1.65;-webkit-font-smoothing:antialiased}
.wrap{max-width:60rem;margin:0 auto;padding:0 1.75rem}
/* The dot field. A halftone made of one repeating radial-gradient, faded out
along the diagonal by a mask so it reads as a wave rather than wallpaper. */
/* No overflow clip here: the dot field is inset to the box already, and a clip
would cut off the copy-prompt menu. */
.hero{position:relative;border-bottom:1px solid var(--line)}
.hero::before{content:"";position:absolute;inset:0;
background-image:radial-gradient(var(--line-hi) 1px, transparent 1px);
background-size:7px 7px;
-webkit-mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
pointer-events:none}
.hero .wrap{position:relative;padding-top:5.5rem;padding-bottom:4rem}
nav{border-bottom:1px solid var(--line)}
nav .in{max-width:60rem;margin:0 auto;padding:1.1rem 1.75rem;display:flex;
justify-content:space-between;align-items:center;gap:1rem}
.brand{font-family:var(--mono);font-size:.85rem;letter-spacing:.14em;
text-transform:uppercase;color:var(--ink);text-decoration:none;
display:inline-flex;align-items:center;gap:.6rem}
.brand i{font-style:normal;color:var(--faint)}
.mark{width:1.15em;height:1.15em;display:block;flex:0 0 auto}
nav a.up{font-family:var(--mono);font-size:.72rem;letter-spacing:.14em;
text-transform:uppercase;color:var(--soft);text-decoration:none}
nav a.up:hover{color:var(--ink)}
h1{font-family:var(--mono);font-size:clamp(2rem,5.4vw,3.4rem);line-height:1.12;
letter-spacing:-.02em;margin:0 0 1.1rem;font-weight:500;text-wrap:balance}
h1 em{font-style:normal;color:var(--faint)}
.lede{color:var(--soft);font-size:1.05rem;max-width:52ch;margin:0 0 2.25rem}
.btns{display:flex;flex-wrap:wrap;gap:.7rem;margin:0 0 .5rem;align-items:center}
.btn{display:inline-flex;align-items:center;gap:.5rem;font-family:var(--mono);
font-size:.72rem;letter-spacing:.14em;text-transform:uppercase;
padding:.8rem 1.4rem;border:1px solid var(--line-hi);border-radius:var(--r);
color:var(--ink);text-decoration:none;background:transparent;cursor:pointer;
line-height:1.2;font-weight:400}
.btn:hover{background:#141414;text-decoration:none;border-color:var(--soft)}
.btn.solid{background:var(--ink);color:#000;border-color:var(--ink)}
.btn.solid:hover{background:#d8d8d4}
.btn .chev{width:.7em;height:.7em;flex:0 0 auto;transition:transform .15s ease}
.btn[aria-expanded="true"] .chev{transform:rotate(180deg)}
/* Copy-prompt selector. Each row copies the prompt for its own target. */
.copy{position:relative;display:inline-flex}
.menu{position:absolute;top:calc(100% + .5rem);left:0;z-index:20;min-width:21rem;
background:var(--panel);border:1px solid var(--line-hi);border-radius:var(--r-soft);
padding:.4rem;display:flex;flex-direction:column;
box-shadow:0 12px 32px rgba(0,0,0,.75)}
.menu[hidden]{display:none}
.mi{display:flex;align-items:center;gap:.7rem;width:100%;text-align:left;
padding:.62rem .8rem;border:0;border-radius:calc(var(--r-soft) - .35rem);
background:transparent;color:var(--ink);font-family:var(--mono);font-size:.76rem;
letter-spacing:.04em;text-decoration:none;cursor:pointer;line-height:1.3;
white-space:nowrap}
.mi:hover,.mi:focus-visible{background:#181818;outline:none}
.mi .mark{width:1.05rem;height:1.05rem;color:var(--soft)}
.mi:hover .mark{color:var(--ink)}
.mi u{margin-left:auto;color:var(--faint);text-decoration:none;font-size:.68rem;
letter-spacing:.1em;text-transform:uppercase}
/* Works-with bar: one scrolling row, name and mark per agent. */
.strip{border-bottom:1px solid var(--line);background:var(--panel)}
.strip .in{max-width:60rem;margin:0 auto;padding:.9rem 1.75rem;display:flex;
align-items:center;gap:1.25rem;font-family:var(--mono);font-size:.72rem;
letter-spacing:.1em;text-transform:uppercase;color:var(--faint)}
.strip b{color:var(--soft);font-weight:400;flex:0 0 auto;
border-right:1px solid var(--line);padding-right:1.25rem;align-self:stretch;
display:flex;align-items:center}
.bar{display:flex;align-items:center;gap:.5rem;flex:1 1 auto;min-width:0;
overflow-x:auto;scrollbar-width:none;scroll-snap-type:x proximity;
-webkit-overflow-scrolling:touch;
-webkit-mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent);
mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent)}
.bar::-webkit-scrollbar{display:none}
.agent{display:inline-flex;align-items:center;gap:.45rem;flex:0 0 auto;
padding:.4rem .85rem;border:1px solid var(--line);border-radius:var(--r);
color:var(--soft);white-space:nowrap;scroll-snap-align:start;
text-decoration:none;background:var(--ground)}
.agent:hover{color:var(--ink);border-color:var(--line-hi);text-decoration:none}
.agent .mark{width:.95rem;height:.95rem}
h2{font-family:var(--mono);font-size:1.1rem;letter-spacing:-.01em;margin:2.75rem 0 .75rem;font-weight:500}
h3{font-size:1rem;margin:2rem 0 .5rem;font-weight:600}
h4,h5,h6{font-size:.94rem;margin:1.5rem 0 .5rem;font-weight:600}
p{margin:0 0 1rem;max-width:70ch}
ul,ol{margin:0 0 1rem;padding-left:1.35rem;max-width:70ch}
li{margin:.22rem 0}
a{color:var(--ink);text-decoration:underline;text-underline-offset:3px;
text-decoration-color:var(--line-hi)}
a:hover{text-decoration-color:var(--ink)}
a:focus-visible{outline:1px solid var(--ink);outline-offset:3px}
code{font-family:var(--mono);font-size:.85em;background:var(--panel);
border:1px solid var(--line);border-radius:5px;padding:.1em .36em}
pre{background:var(--panel);border:1px solid var(--line);padding:1rem 1.1rem;
border-radius:var(--r-soft);overflow-x:auto;margin:0 0 1.25rem}
pre code{background:none;border:0;padding:0;font-size:.82rem;line-height:1.7}
blockquote{margin:0 0 1rem;padding-left:1rem;border-left:1px solid var(--line-hi);color:var(--soft)}
hr{border:0;border-top:1px solid var(--line);margin:2.5rem 0}
table{border-collapse:collapse;width:100%;margin:0 0 1.25rem;font-size:.92rem;
display:block;overflow-x:auto}
th,td{border:1px solid var(--line);padding:.5rem .7rem;text-align:left}
.curl{display:block;background:var(--panel);border:1px solid var(--line);
border-radius:var(--r-soft);padding:.95rem 1.1rem;font-family:var(--mono);
font-size:.8rem;color:var(--soft);overflow-x:auto;margin:0 0 2.5rem;
white-space:pre;line-height:1.9}
.curl b{color:var(--ink);font-weight:400}
.curl i{font-style:normal;color:var(--faint)}
/* index */
#q{width:100%;padding:.85rem 1.2rem;font-family:var(--mono);font-size:.85rem;color:var(--ink);
background:var(--panel);border:1px solid var(--line);border-radius:var(--r);margin:0 0 .6rem}
#q::placeholder{color:var(--faint);text-transform:uppercase;letter-spacing:.1em;font-size:.72rem}
#q:focus{outline:none;border-color:var(--soft)}
#count{color:var(--faint);font-family:var(--mono);font-size:.72rem;letter-spacing:.1em;
text-transform:uppercase;margin:0 0 2rem}
.cat{margin:2.5rem 0 .5rem;font-family:var(--mono);font-size:.7rem;letter-spacing:.16em;
text-transform:uppercase;color:var(--faint);border-bottom:1px solid var(--line);
padding-bottom:.45rem}
.row{display:block;padding:.6rem .9rem;margin:0 -.9rem;border-bottom:1px solid var(--line);
border-radius:var(--r-soft);text-decoration:none}
.row:hover{background:#0a0a0a}
.nm{font-family:var(--mono);font-size:.84rem;color:var(--ink);display:block}
.ds{color:var(--soft);font-size:.9rem;display:block;margin-top:.12rem}
footer{margin-top:4rem;padding:2rem 0 4rem;border-top:1px solid var(--line);
color:var(--faint);font-size:.85rem}
footer a{color:var(--soft)}
.fmap{display:grid;gap:1.75rem;grid-template-columns:repeat(auto-fit,minmax(11rem,1fr));
margin:0 0 2rem;font-size:.85rem}
.fmap b{display:block;font-family:var(--mono);font-size:.68rem;letter-spacing:.16em;
text-transform:uppercase;color:var(--faint);font-weight:400;margin:0 0 .6rem;
border-bottom:1px solid var(--line);padding-bottom:.4rem}
.fmap a{display:inline-block;color:var(--ink);text-decoration:none;margin:.3rem .35rem 0 0}
.fmap a:hover{text-decoration:underline}
.fmap div{color:var(--faint);line-height:1.5}
.fend{border-top:1px solid var(--line);padding-top:1.25rem;font-size:.82rem}
@media (max-width:640px){
.hero .wrap{padding-top:3.25rem;padding-bottom:2.75rem}
.btns{gap:.5rem}
.btn{padding:.75rem 1.15rem;font-size:.68rem}
.copy,.copy .btn{width:100%;justify-content:center}
.menu{left:0;right:0;min-width:0}
.strip .in{flex-direction:column;align-items:flex-start;gap:.6rem;padding:.9rem 1.75rem}
.strip b{border-right:0;padding-right:0}
.bar{width:100%}
}
</style>
<link rel="alternate" type="text/markdown" href="/hanzo-koe.md">
<link rel="icon" href="/favicon.svg">
<link rel="canonical" href="https://hanzoskills.com/hanzo-koe">
</head>
<!-- Reading this with a machine? Every page here is also plain markdown.
This one: https://hanzoskills.com/hanzo-koe.md
Index: https://hanzoskills.com/llms.txt
Corpus: https://hanzoskills.com/all.md
Append .md to any path for the markdown twin. -->
<body>
<nav><div class="in">
<a class="brand" href="/"><svg class="mark" viewBox="0 0 67 67" fill="currentColor" aria-hidden="true"><path d="M22.21 67V44.6369H0V67H22.21Z"/><path d="M66.7038 22.3184H22.2534L0.0878906 44.6367H44.4634L66.7038 22.3184Z"/><path d="M22.21 0H0V22.3184H22.21V0Z"/><path d="M66.7198 0H44.5098V22.3184H66.7198V0Z"/><path d="M66.7198 67V44.6369H44.5098V67H66.7198Z"/></svg> HANZO<i>SKILLS</i></a>
<a class="up" href="/">All skills</a>
</div></nav>
<div class="wrap">
<h1>hanzo-koe</h1><p class="lede">Koe is a 1.6B parameter text-to-speech model that directly generates realistic multi-speaker dialogue from text transcripts.</p><h1>Hanzo Koe - Text-to-Dialogue Model</h1>
<p><strong>Category</strong>: Hanzo Ecosystem <strong>Related Skills</strong>: <code>hanzo/hanzo-mugen.md</code>, <code>hanzo/hanzo-engine.md</code>, <code>hanzo/hanzo-ml.md</code></p>
<h2>Overview</h2>
<p>Koe is a <strong>1.6B parameter text-to-speech model</strong> that directly generates realistic multi-speaker dialogue from text transcripts. It supports two-speaker conversations with speaker tags (<code>[S1]</code>, <code>[S2]</code>), non-verbal sounds (laughter, coughs, sighs), and voice cloning from audio prompts.</p>
<p>The architecture uses an <strong>encoder-decoder transformer</strong> with RoPE positional embeddings. The encoder processes text tokens, and the decoder autoregressively generates 9-channel audio codes that are decoded by the Descript Audio Codec (DAC) into 44.1kHz waveforms.</p>
<h3>Key Capabilities</h3>
<ul><li><strong>Multi-speaker dialogue</strong>: Generate conversations between two speakers from tagged transcripts</li><li><strong>Non-verbal generation</strong>: Produce laughter, coughs, throat clearing, sighs, gasps, etc.</li><li><strong>Voice cloning</strong>: Condition output on reference audio (5-10 seconds) for speaker consistency</li><li><strong>Real-time generation</strong>: Up to 2.2x realtime factor with torch.compile on RTX 4090</li></ul>
<h2>When to use</h2>
<ul><li>Generating dialogue audio from scripts with speaker annotations</li><li>Voice cloning and style transfer from reference audio</li><li>Adding non-verbal vocalizations to synthesized speech</li><li>Multi-speaker TTS without per-speaker fine-tuning</li></ul>
<h2>Hard requirements</h2>
<ol><li><strong>Python 3.10+</strong> with PyTorch 2.6</li><li><strong>GPU</strong>: CUDA or MPS (Apple Silicon with torch.compile disabled)</li><li><strong>VRAM</strong>: ~10GB (float16/bfloat16), ~13GB (float32)</li><li><strong>HF_TOKEN</strong>: Required for downloading model config from HuggingFace Hub</li></ol>
<h2>Quick reference</h2>
<p>| Item | Value | |------|-------| | Repo | <code>github.com/hanzoai/koe</code> | | Branch | <code>main</code> | | Language | Python | | Parameters | 1.6B | | Package | <code>nari-tts</code> | | Sample Rate | 44.1kHz | | Audio Channels | 9 (DAC codebooks) | | Install | <code>pip install git+https://github.com/hanzoai/koe.git</code> | | Run UI | <code>uv run app.py</code> | | License | Apache 2.0 |</p>
<h2>Architecture</h2>
<pre><code>Text Input: &quot;[S1] Hello. [S2] Hi there. (laughs)&quot;
|
v
┌─────────────────────────────┐
│ Text Tokenizer │
│ src_vocab_size: 128 │
│ text_length: padded to 128 │
└──────────┬──────────────────┘
|
v
┌─────────────────────────────┐
│ Encoder (Transformer) │
│ n_layer layers │
│ n_head attention heads │
│ head_dim per head │
│ RoPE positional encoding │
│ RMSNorm normalization │
│ DenseGeneral (tensordot) │
└──────────┬──────────────────┘
|
v
┌─────────────────────────────┐
│ Decoder (Transformer) │
│ Cross-attention to encoder │
│ 9-channel audio code output │
│ tgt_vocab_size: 1028 │
│ Special tokens: │
│ EOS=1024, PAD=1025, │
│ BOS=1026 │
│ Delay pattern: [0,8..15] │
└──────────┬──────────────────┘
|
v
┌─────────────────────────────┐
│ Descript Audio Codec (DAC) │
│ Decode 9 codebook streams │
│ Output: 44.1kHz waveform │
└─────────────────────────────┘</code></pre>
<h3>Audio Delay Pattern</h3>
<p>The decoder uses a delay pattern across 9 channels: <code>[0, 8, 9, 10, 11, 12, 13, 14, 15]</code>. This staggers codebook generation to improve coherence across the multi-stream output. Token positions are shifted via pre-computed delay/revert indices.</p>
<h3>Inference Sampling</h3>
<p>Token generation uses configurable sampling:</p>
<ul><li><strong>Temperature</strong>: Controls randomness (0.0 = greedy argmax)</li><li><strong>Top-p</strong>: Nucleus sampling with cumulative probability threshold</li><li><strong>Top-k</strong>: Limits candidate tokens to top-k logits</li><li><strong>EOS suppression</strong>: EOS token masked unless it has the highest logit</li></ul>
<h2>One-file quickstart</h2>
<pre><code class="lang-python">from dia.model import Dia
model = Dia.from_pretrained(&quot;nari-labs/Dia-1.6B&quot;, compute_dtype=&quot;float16&quot;)
text = &quot;[S1] Koe is a text to dialogue model. [S2] You get full control over scripts and voices. [S1] Wow. Amazing. (laughs) [S2] Try it now.&quot;
output = model.generate(text, use_torch_compile=True, verbose=True)
model.save_audio(&quot;dialogue.mp3&quot;, output)</code></pre>
<h3>Voice Cloning</h3>
<pre><code class="lang-python">from dia.model import Dia
model = Dia.from_pretrained(&quot;nari-labs/Dia-1.6B&quot;, compute_dtype=&quot;float16&quot;)
# Provide transcript of reference audio before generation text
text = &quot;[S1] This is the reference speaker talking. [S2] And this is another voice. [S1] Now generate new content in my voice.&quot;
output = model.generate(
text,
audio_prompt=&quot;reference_audio.mp3&quot;, # 5-10 seconds
use_torch_compile=True,
)
model.save_audio(&quot;cloned.mp3&quot;, output)</code></pre>
<h3>Apple Silicon (MPS)</h3>
<pre><code class="lang-python">from dia.model import Dia
model = Dia.from_pretrained(&quot;nari-labs/Dia-1.6B&quot;, compute_dtype=&quot;float16&quot;)
# torch.compile not supported on MPS
output = model.generate(text, use_torch_compile=False, verbose=True)</code></pre>
<h2>Non-Verbal Tags</h2>
<p>Recognized tags (place in transcript where desired):</p>
<p><code>(laughs)</code>, <code>(clears throat)</code>, <code>(sighs)</code>, <code>(gasps)</code>, <code>(coughs)</code>, <code>(singing)</code>, <code>(sings)</code>, <code>(mumbles)</code>, <code>(beep)</code>, <code>(groans)</code>, <code>(sniffs)</code>, <code>(claps)</code>, <code>(screams)</code>, <code>(inhales)</code>, <code>(exhales)</code>, <code>(applause)</code>, <code>(burps)</code>, <code>(humming)</code>, <code>(sneezes)</code>, <code>(chuckle)</code>, <code>(whistles)</code></p>
<h2>Performance</h2>
<p>| Precision | Realtime Factor (compile) | Realtime Factor (no compile) | VRAM | |-----------|---------------------------|------------------------------|------| | bfloat16 | 2.1x | 1.5x | ~10GB | | float16 | 2.2x | 1.3x | ~10GB | | float32 | 1.0x | 0.9x | ~13GB |</p>
<p>Benchmarked on RTX 4090.</p>
<h2>Dependencies</h2>
<pre><code>descript-audio-codec&gt;=1.0.0
gradio&gt;=5.25.2
huggingface-hub&gt;=0.30.2
numpy&gt;=2.2.4
pydantic&gt;=2.11.3
safetensors&gt;=0.5.3
soundfile&gt;=0.13.1
torch==2.6.0
torchaudio==2.6.0
triton==3.2.0 (Linux)</code></pre>
<h2>Project Structure</h2>
<pre><code>koe/
├── dia/
│ ├── __init__.py
│ ├── audio.py # Delay pattern indices, audio processing
│ ├── config.py # DiaConfig (Pydantic): data, encoder, decoder, model
│ ├── layers.py # DiaModel: DenseGeneral, transformer blocks, attention
│ ├── model.py # Dia: main model class, generate(), save_audio()
│ ├── state.py # Inference state: KV cache, decoder/encoder state
│ └── static/images/ # Banner assets
├── docker/
│ ├── Dockerfile.cpu
│ └── Dockerfile.gpu
├── example/
│ ├── benchmark.py
│ ├── simple.py
│ ├── simple-mac.py
│ ├── simple_batch.py
│ ├── voice_clone.py
│ └── voice_clone_batch.py
├── app.py # Gradio web UI
├── cli.py # CLI interface
├── pyproject.toml
└── uv.lock</code></pre>
<h2>Generation Guidelines</h2>
<ul><li>Input text should correspond to 5-20 seconds of audio for best quality</li><li>Always begin with <code>[S1]</code> and alternate between <code>[S1]</code> and <code>[S2]</code></li><li>Use non-verbal tags sparingly; overuse causes artifacts</li><li>For voice cloning: provide 5-10 second reference audio with matching transcript</li><li>End text with the second-to-last speaker tag to improve trailing audio quality</li><li>1 second of audio is approximately 86 tokens</li></ul>
<h2>Related Skills</h2>
<ul><li><code>hanzo/hanzo-mugen.md</code> - Audio generation (music, sound effects)</li><li><code>hanzo/hanzo-engine.md</code> - Model serving infrastructure</li><li><code>hanzo/hanzo-ml.md</code> - Rust ML framework</li></ul>
<hr>
<p><strong>Last Updated</strong>: 2026-03-13 <strong>Category</strong>: Hanzo Ecosystem <strong>Related</strong>: tts, dialogue, speech-synthesis, voice-cloning, audio <strong>Prerequisites</strong>: Python, PyTorch, audio processing concepts</p>
<footer>
<div class="fmap">
<div><b>Build</b>
<a href="https://hanzo.app">hanzo.app</a> app builder
<a href="https://hanzo.codes">hanzo.codes</a> code with an agent
<a href="https://hanzoskills.com">hanzoskills.com</a> what an agent reads</div>
<div><b>Run</b>
<a href="https://console.hanzo.ai">console.hanzo.ai</a> cloud console
<a href="https://api.hanzo.ai">api.hanzo.ai</a> the API</div>
<div><b>Account</b>
<a href="https://hanzo.id">hanzo.id</a> sign in
<a href="https://pay.hanzo.ai">pay.hanzo.ai</a> top up
<a href="https://billing.hanzo.ai">billing.hanzo.ai</a> invoices and usage</div>
<div><b>Company</b>
<a href="https://hanzo.ai">hanzo.ai</a> canonical
<a href="https://hanzo.ventures">hanzo.ventures</a> ventures</div>
</div>
<div class="fend"><a href="/hanzo-koe.md">This page as plain text</a> · <a href="/llms.txt">Index for agents</a></div>
</footer>
</div></body></html>