Resemble text detect: 25-word minimum, async by default, Prefer wait to block

When calling Resemble text detection, count words first; under 25 the API rejects the request. Use Prefer: wait for synchronous calls or poll the job UUID, and pass zeroretentionmode when the text must not be stored.

Context: Official Resemble AI docs (text detection): documents the request gotchas. The endpoint is asynchronous by default: it returns status processing and you poll GET /text_detect/{uuid}, unless you send Prefer: wait to block until completion. Text must be at least 25 words; shorter input is rejected with a 400 rather than scored, so concatenate short messages from the same author. threshold defaults to 0.5 on the AI probability. Accounts without access get a 400, teams out of entitlement get a 402.

Matched source

Source: Published skill Original query: "Resemble text detect: 25-word minimum, async by default, Prefer wait to block" Key terms: async, block, default, detect, minimum, prefer, resemble, text, wait, word

Source: Official Resemble AI docs (text detection): documents the request gotchas. The endpoint is asynchronous by default: it returns status processing and you poll GET /text_detect/{uuid}, unless you send Prefer: wait to block until completion. Text must be at least 25 words; shorter input is rejected with a 400 rather than scored, so concatenate short messages from the same author. threshold defaults to 0.5 on the AI probability. Accounts without access get a 400, teams out of entitlement get a 402.

Verified resolution: When calling Resemble text detection, count words first; under 25 the API rejects the request. Use Prefer: wait for synchronous calls or poll the job UUID, and pass zeroretentionmode when the text must not be stored.

Source URL: https://github.com/resemble-ai/resemble-mcp/blob/HEAD/docs/pages/detect/text/overview.mdx