# Japan Furigana API

> Japan Furigana API is a paid API for AI agents from furigana.agentic-jp.com, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-15).

Converts Japanese kanji text to furigana (hiragana readings) or romaji, with part-of-speech tagging, multi-candidate name readings, and text classification

## Facts

- Endpoint: POST https://furigana.agentic-jp.com/furigana
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/japan-furigana-api-cb0f69c7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_e8nNg06k-cO0_UyR1qhN7

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability japan-furigana-api-cb0f69c7 -d '<json body>'
```

Example prompt: What's the furigana reading for '東京都千代田区永田町'? Break it into tokens with their part-of-speech tags and hiragana readings.

## When to prefer this

Use this endpoint when you need accurate kanji-to-furigana conversion with linguistic metadata (part-of-speech, token segmentation) for Japanese text, especially for proper nouns and place names. Prefer over general translation APIs when you specifically need phonetic readings rather than meaning. Ideal for accessibility tools, language learning apps, or any pipeline that must annotate Japanese text with pronunciation.

## Known failure modes

- Non-Japanese or empty input may return an error or empty token list
- Payment failure via x402 if USDC balance is insufficient
- Ambiguous Japanese names may return multiple candidate readings requiring disambiguation
- Rate limiting if too many concurrent requests are made

## How this service works

Convert kanji-mixed Japanese (JP) text to hiragana, katakana, or romaji (Hepburn/Nippon/Passport), with a per-token breakdown of surface form, reading, and part-of-speech. Backed by the kuromoji morphological analyzer. Use to generate ruby readings, build search indexes, or preprocess text for speech synthesis.

## Output

A JSON object containing the full furigana reading of the input string (e.g. 'とうきょうとちよだくながたちょう'), plus a token array where each token includes the surface form (original kanji), its hiragana reading, and part-of-speech category (e.g. 名詞 for noun).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "maxLength": 5000,
   "description": "Japanese kanji-mixed text to convert to a reading"
  },
  "options": {
   "type": "object",
   "properties": {
    "to": {
     "enum": [
      "hiragana",
      "katakana",
      "romaji"
     ],
     "type": "string"
    },
    "mode": {
     "enum": [
      "normal",
      "furigana",
      "okurigana"
     ],
     "type": "string"
    },
    "romaji_style": {
     "enum": [
      "hepburn",
      "nippon",
      "passport"
     ],
     "type": "string"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "input": "東京都千代田区永田町",
  "result": "とうきょうとちよだくながたちょう",
  "tokens": [
   {
    "pos": "名詞",
    "reading": "とうきょう",
    "surface": "東京"
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/japan-furigana-api-cb0f69c7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from furigana.agentic-jp.com](https://www.zero.xyz/host/furigana.agentic-jp.com/llms.txt)