# Busker Language ID

> Busker Language ID is a paid API for AI agents from workbot1.oddsys.org, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-11).

Identifies the natural language of a text snippet from 180+ languages, returning ISO 639-3/639-1 codes, English name, ranked candidates, and confidence margin.

## Facts

- Endpoint: POST https://workbot1.oddsys.org/lang?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-11
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/busker-language-id-5ac5958c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_HhuVkORL2KBnWxyER1K9Q

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 busker-language-id-5ac5958c -d '<json body>'
```

Example prompt: What language is this text written in — give me the top 3 candidates with confidence: 'Bonjour, comment allez-vous aujourd'hui? J'espère que tout va bien.'

## When to prefer this

Choose this endpoint when you need fast, cheap ($0.001/call) language identification across a broad set of 180+ languages with standardized ISO 639-3 and ISO 639-1 codes and ranked confidence scores. It supports batching up to 100 texts per call, making it efficient for bulk processing. Prefer it over generic LLM-based detection when you need deterministic structured output, consistent code formats, and the ability to restrict candidates to a known language subset.

## Known failure modes

- Text shorter than 10 characters is rejected as insufficient for reliable detection
- Ambiguous or mixed-language text may yield low-confidence results with several near-equal candidates
- Very rare languages below 1M speakers may not be recognized or may be misclassified as a related language
- Invalid ISO 639-3 codes in the 'only' filter will cause validation errors
- Batch exceeding 100 texts will be rejected
- Empty text or whitespace-only input will fail validation

## How this service works

Language identification for 180+ languages (every language with ≥1M speakers): ISO 639-3 code, ISO 639-1 code and English name, with ranked candidates and a confidence margin. Single text or batches up to 100.

## Output

Returns ranked language candidates (up to 10), each with ISO 639-3 code, ISO 639-1 code, English language name, and a confidence margin indicating how certain the model is. For batch requests, results are returned per-text in the same order as input.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "top": {
   "type": "integer",
   "description": "Number of ranked candidates to return (1-10, default 3)."
  },
  "only": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "Restrict to these ISO 639-3 codes (e.g. [\"eng\",\"deu\",\"fra\"])."
  },
  "text": {
   "type": "string",
   "description": "Text to identify (≥10 characters)."
  },
  "texts": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "maxItems": 100,
   "description": "Batch of texts."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/busker-language-id-5ac5958c/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from workbot1.oddsys.org](https://www.zero.xyz/host/workbot1.oddsys.org/llms.txt)