# ThaiKit Thai Text Normalizer

> ThaiKit Thai Text Normalizer is a paid API for AI agents from api.thaikit.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-11-03).

Cleans and normalizes Thai text by fixing encoding artifacts, misplaced tone marks, duplicate marks, invisible characters, and space issues, with optional digit conversion

## Facts

- Endpoint: POST https://api.thaikit.dev/normalize?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-03
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/thaikit-thai-text-normalizer-98853aad
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_rCsp0cf0mlvFpw9gXG9DA

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 thaikit-thai-text-normalizer-98853aad -d '<json body>'
```

Example prompt: Can you clean up this Thai text so it works properly in search and matching? The string is 'สวัสดีครับ เเมว' — fix any encoding artifacts like เเ vs แ, misplaced tone marks, or invisible characters, and convert any Thai digits to Arabic numerals.

## When to prefer this

Choose this endpoint when you need to canonicalize Thai text before storage, search indexing, string matching, or deduplication, especially when source data comes from OCR, copy-paste, or mixed keyboard inputs that may contain visually identical but byte-different representations of Thai characters. It is the right choice when you need an audit trail of exactly what was fixed.

## Known failure modes

- Text exceeds 5000 character limit — request rejected
- Invalid digits enum value — validation error returned
- Non-Thai or empty text — may return unchanged with no fixes listed
- Network timeout on large complex strings
- Payment failure via x402 protocol — call blocked

## How this service works

Clean up Thai text that looks right but is stored wrongly, which breaks search, matching and deduplication: joins ํ + า into ำ, เเ into แ, reorders misplaced tone marks, removes duplicated marks, zero-width and other invisible characters, fixes odd spaces, and optionally converts Thai/Arabic digits. Returns every fix made. Body: {"text": "...", "digits": "keep|arabic|thai"} (max 5000 chars)

## Output

Returns the normalized Thai text with all fixes applied, along with a list describing every correction made — such as เเ→แ merges, ํา joins into ำ, tone mark reorderings, removed zero-width or invisible characters, fixed spaces, and any digit conversions performed.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "maxLength": 5000,
   "description": "Thai text to clean"
  },
  "digits": {
   "enum": [
    "keep",
    "arabic",
    "thai"
   ],
   "type": "string",
   "description": "keep (default), arabic (๑ -> 1) or thai (1 -> ๑)"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/thaikit-thai-text-normalizer-98853aad/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.thaikit.dev](https://www.zero.xyz/host/api.thaikit.dev/llms.txt)