# Japanese Text Normalizer (furigana.agentic-jp.com)

> Japanese Text Normalizer (furigana.agentic-jp.com) is a paid API for AI agents from furigana.agentic-jp.com, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-15).

Normalizes Japanese text by converting fullwidth/halfwidth characters, folding halfwidth katakana, removing invisible characters, and cleaning whitespace, with per-change logging.

## Facts

- Endpoint: POST https://furigana.agentic-jp.com/normalize
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/japanese-text-normalizer-furigana-agentic-jp-com-994c37a1
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_2atwSxG33c8w59_IWM2FD

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 japanese-text-normalizer-furigana-agentic-jp-com-994c37a1 -d '<json body>'
```

Example prompt: Normalize this Japanese text so that fullwidth and halfwidth characters are unified and any invisible characters are removed: '東京　ＡＢＣ　ﾄｳｷｮｳ　test' — turn on all normalization options.

## When to prefer this

Use this endpoint when you need to canonicalize Japanese text for deduplication, matching, or storage — especially when input may contain mixed fullwidth/halfwidth forms, halfwidth katakana (e.g. from legacy systems or mobile input), zero-width or invisible Unicode characters, or inconsistent whitespace. Prefer this over generic Unicode normalization libraries when you need a per-change audit log and toggleable transformations specific to Japanese character encoding conventions.

## Known failure modes

- Input text exceeds 5000 character limit — API returns validation error
- Non-Japanese or non-Unicode text passed — may return unchanged or partial normalization
- Invalid options object structure — API may ignore or error on unknown toggle keys
- Network timeout for large payloads near the character limit
- Payment failure via x402 protocol — call not executed

## How this service works

Normalize Japanese (JP) text to a canonical form: fullwidth↔halfwidth conversion, halfwidth-katakana folding, invisible-character removal, and whitespace cleanup — each transformation toggleable. Returns a per-change log. Use to deduplicate or match text where '東京' and 'ﾄｳｷｮｳ' must compare equal.

## Output

Returns the normalized Japanese text string along with a per-change log detailing each transformation applied (e.g. which characters were converted, removed, or adjusted), enabling the caller to audit exactly what changed.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "maxLength": 5000,
   "description": "Japanese text to normalize (fullwidth/halfwidth, kana, invisibles)"
  },
  "options": {
   "type": "object"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "input": "ｱｲｳ　ＡＢＣ　１２３",
  "changes": [
   {
    "type": "halfwidth_kana_to_fullwidth",
    "count": 3
   }
  ],
  "normalized": "アイウ ABC 123"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/japanese-text-normalizer-furigana-agentic-jp-com-994c37a1/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)