Skip to main content
When you don’t need to build an entire document, three focused endpoints let you work with short snippets of text: humanize a machine-sounding draft, rewrite a passage to a custom instruction, or draft a fresh section from a prompt. All three return structured JSON — no file is produced. These are the same helpers the Overten web app uses inside its inline editor, exposed for your own integrations with one sk_live_* key.

​
Humanize

Rewrite text so it reads like a person wrote it — keeps meaning, drops AI tells. 
curl -X POST "https://backend.overtenai.com/api/v1/text/humanize" \
  -H "X-API-Key: $OVERTEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "In conclusion, it is imperative that stakeholders engage..."
  }'
Response
{
  "text": "To wrap up: stakeholders need to get involved..."
}

​
Rewrite

Rewrite text to your own instruction — tone, length, style, audience, etc. 
curl -X POST "https://backend.overtenai.com/api/v1/text/rewrite" \
  -H "X-API-Key: $OVERTEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Make it more formal and trim it to one sentence",
    "text": "Hey team — just a heads up, the release is pushed to Friday because of the flaky test."
  }'
Response
{
  "text": "The release has been rescheduled to Friday due to an intermittent test failure."
}
The prompt field carries the instruction; the text field is the passage to transform.

​
New content

Draft a fresh section from a prompt. Useful for filling in a missing section of an outline before you generate the full document. 
curl -X POST "https://backend.overtenai.com/api/v1/text/new-content" \
  -H "X-API-Key: $OVERTEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A 3-paragraph executive summary about Q3 EMEA revenue slipping 4% from forecast, mostly driven by DACH softness.",
    "file_name": "Q3_review.docx"
  }'
Response
{
  "text": "Executive summary\n\nQ3 EMEA revenue came in 4% below forecast..."
}
file_name is an optional hint — the model uses it to tune tone/length to the target document type (a .docx briefing reads differently from a .pptx slide). Leave it out if you don’t care.

​
Request limits

Endpointtext maxprompt max
/text/humanize20,000 chars—
/text/rewrite20,000 chars2,000 chars
/text/new-content—5,000 chars
For longer bodies, chunk on paragraph or section boundaries and stitch results client-side.

​
Errors

Same shape as the rest of the API: 
{
  "success": false,
  "error": "permission_denied",
  "message": "Your viewer role in this workspace doesn't allow creating content."
}
See Errors for the full list.
These endpoints run on a smaller, faster model than /excel/generate et al. — most calls return in under 3 seconds. No sync/async split; you always get the answer in the response.