For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Status
OverviewProductsManageAPI ReferenceTutorialsClient Libraries
OverviewProductsManageAPI ReferenceTutorialsClient Libraries
  • Voice Generation
    • Speech-to-Speech
  • Voice Creation
      • Overview
      • Generate Candidates
      • Create from Candidate
  • Voice Tools
  • Real-Time Agents
    • Overview
  • Safety & Detection
Status
LogoLogo
Voice CreationVoice Design

Generate Voice Candidates

Was this page helpful?
Previous

Create Voice from Candidate

Next
Built with

POST https://app.resemble.ai/api/v2/voice-design

Generate voice candidates based on a text prompt describing desired voice characteristics.

FieldTypeRequiredNotes
user_promptstring✅Description of desired voice (e.g., “A warm, friendly female voice with a British accent”).
is_voice_design_trialboolean❌Whether this is a trial generation. Default: true.
$curl --request POST 'https://app.resemble.ai/api/v2/voice-design' \
> -H 'Authorization: Bearer YOUR_API_TOKEN' \
> -H 'Content-Type: application/json' \
> --data '{
> "user_prompt": "A warm, friendly female voice with a British accent",
> "is_voice_design_trial": true
> }'
1{
2 "voice_candidates": {
3 "voice_design_model_uuid": "VOICE_DESIGN_UUID",
4 "samples": [
5 {
6 "audio_url": "https://...",
7 "sample_index": 0
8 },
9 {
10 "audio_url": "https://...",
11 "sample_index": 1
12 },
13 {
14 "audio_url": "https://...",
15 "sample_index": 2
16 }
17 ]
18 }
19}

Free users are limited to one trial. Processing is synchronous. Returns multiple voice samples to choose from. Audio URLs expire in 4 hours.