---
title: "Design a new voice from a character description (such as \"deep-voiced warrior\" or \"cheerful young girl\") and have it speak a short line of text, returning a sample of that newly created voice. Both voice_description and text are required, the spoken text is limited to 200 characters or the call returns HTTP 400, and type selects \"human\" or \"non-human\" voices. Synchronous: the call blocks until generation finishes and returns a single audio result containing a URL; there is no separate polling step. Credits are charged on success. Use this to invent and audition a voice from a description; use createSpeech for text-to-speech that clones a specific voice from an audio sample, and createSpeechPreset for text-to-speech using a named preset voice. Pass an optional request_id to tag the result so you can locate it later via getAudioResults. Requires an API key (user scope)."
method: POST
path: "/audio/voice"
tags: ["Audio"]
---

# Design a new voice from a character description (such as "deep-voiced warrior" or "cheerful young girl") and have it speak a short line of text, returning a sample of that newly created voice. Both voice_description and text are required, the spoken text is limited to 200 characters or the call returns HTTP 400, and type selects "human" or "non-human" voices. Synchronous: the call blocks until generation finishes and returns a single audio result containing a URL; there is no separate polling step. Credits are charged on success. Use this to invent and audition a voice from a description; use createSpeech for text-to-speech that clones a specific voice from an audio sample, and createSpeechPreset for text-to-speech using a named preset voice. Pass an optional request_id to tag the result so you can locate it later via getAudioResults. Requires an API key (user scope).

`POST /audio/voice`

## Request body

- GenerateVoicePayload — Payload for generating a voice sample from a character description
  - `voice_description` string, required — Text description of the voice character (e.g., "deep-voiced warrior", "cheerful young girl").
  - `text` string, required — Text for the voice to speak (max 20 words).
  - `type` 'human' | 'non-human' — Type of voice to generate.
  - `augment_prompt` boolean — Augment the prompt behind the scenes. Disable to have more control.
  - `request_id` string — Optional client-provided identifier for this request. Use this to retrieve results later via the results endpoint.

## Response `200`

Success

- AudioResult
  - `url` string — URL to the generated audio file
  - `type` string
  - `duration` number, float
  - `request_id` string
  - `created_at` integer

## Other responses

- `400` — Error

---

[API](https://skmtc.net/ludo/apis/ludo-ai-api.md) · [All operations](https://skmtc.net/ludo/apis/ludo-ai-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/ludo/ludo-ai-api/revisions/3af866d68651/schema)