Search Tatoeba Sentences
language.tatoeba.searchRead-onlyIdempotent
Retrieve parallel sentences across 429 languages with filters for source language, keyword, audio, and translation language. Sort by relevance, random, or creation date.
Instructions
Search 13M parallel sentences across 429 languages (CC-BY 2.0 FR). Filter by source language, optional translation language, audio availability, and free-text keyword. Sort by relevance/random/created/modified. Tatoeba
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| language | No | ISO 639-3 language code of the source sentence (default "eng"). Use tatoeba.languages to discover codes. | |
| query | No | Optional keyword search inside sentence text. | |
| translation_lang | No | ISO 639-3 code of a target language — only return sentences that have a translation into this language. | |
| has_audio | No | Filter to sentences that have a human audio recording attached. | |
| sort | No | Sort order — "relevance" (default), "words" (length), "created", "modified", or "random". | |
| limit | No | Max sentences to return (default 10, max 50). |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | No | Tool response payload. Shape varies per tool — consult the tool description and inputSchema. May be an object, array, string, or number depending on the upstream provider response. | |
| error | No | Present only when the call failed. Includes error code, message, request_id, and any provider-specific extras. |