# Metaphone Phonetic Encoder

> Metaphone Phonetic Encoder is a paid API for AI agents from similarity.openverbs.com, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-14).

Encodes a single English word using the Metaphone algorithm to produce a phonetic key for pronunciation-based matching.

## Facts

- Endpoint: POST https://similarity.openverbs.com/v1/metaphone
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/metaphone-phonetic-encoder-275ddd83
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_vu-psh7tky03I5K8-HZbL

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 metaphone-phonetic-encoder-275ddd83 -d '<json body>'
```

Example prompt: What's the Metaphone code for the word 'knight'? I want to use it for phonetic name matching.

## When to prefer this

Prefer this endpoint over Soundex when higher phonetic accuracy for English words is needed, especially for longer or more complex words. Choose this over Double Metaphone when only a single canonical code is sufficient and the simpler output is preferable. Use it over Jaro-Winkler or Levenshtein when you need pronunciation-based rather than edit-distance-based similarity.

## Known failure modes

- Empty or missing 'word' field returns a 400 validation error
- Word exceeding 256 characters is rejected
- Non-English or heavily foreign-alphabet words may produce unreliable codes
- Network timeout or 5xx if the service is temporarily unavailable
- Payment failure (x402) if USDC balance is insufficient

## How this service works

Encode a word with the Metaphone algorithm — more accurate than Soundex for English pronunciation.

## Output

Returns the Metaphone phonetic code for the submitted word — a string of consonant sounds representing the English pronunciation, which can be compared against codes of other words to find phonetic matches.

## Request schema (JSON Schema)

```json
{
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "type": "object",
 "properties": {
  "input": {
   "type": "object",
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "type": "string",
     "enum": [
      "POST"
     ]
    },
    "bodyType": {
     "type": "string",
     "enum": [
      "json",
      "form-data",
      "text"
     ]
    },
    "body": {
     "type": "object",
     "properties": {
      "word": {
       "type": "string",
       "minLength": 1,
       "maxLength": 256,
       "description": "The word to encode."
      }
     },
     "required": [
      "word"
     ],
     "additionalProperties": false
    }
   },
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "additionalProperties": false
  }
 },
 "required": [
  "input"
 ]
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/metaphone-phonetic-encoder-275ddd83/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from similarity.openverbs.com](https://www.zero.xyz/host/similarity.openverbs.com/llms.txt)