---
title: "Extract Voice"
method: POST
path: "/api/v1/onboarding/extract-voice"
tags: ["onboarding"]
---

# Extract Voice

`POST /api/v1/onboarding/extract-voice`

## Request

- Base URL: `https://api.nudgelink.co` (the document declares no server; this is the origin it was published from)
- URL: `https://api.nudgelink.co/api/v1/onboarding/extract-voice`
- Auth: HTTP bearer

Doc п.5 — learn the client's real voice from their own writing and store
it as the style_profile, so drafts sound like THEM rather than the
synthetic house default ("Sofia's voice"). The main lever against every
client sounding identical.

## Request body

- ExtractVoiceRequest
  - `writing_samples` string[], required: 3-5 of the client's own posts / past DMs / emails. Their real voice is learned from these.

## Response `200`

Successful Response

- object

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/nudgelink/apis/nudgelink-api.md) · [All operations](https://skmtc.dev/nudgelink/apis/nudgelink-api/llms.txt) · [OpenAPI document](https://skmtc.dev/nudgelink/apis/nudgelink-api/revisions/baa46e6db986?raw)