Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.vmeg.ai/llms.txt

Use this file to discover all available pages before exploring further.

Convert text to speech using a system or cloned voiceId. See Voices for how to obtain IDs.

​
Sync vs async

ModeEndpointResults
SyncPOST /openapi/v1/task/tts/createdata.results[].uri (CDN audio) in HTTP response
AsyncPOST /openapi/v1/task/tts/create-asyncWebhook when event is openapi-tts (data.results)
Every create and create-async call requires X-Idempotency-Key. Async also needs a configured Webhook.

​
Workflow (sync)

See Quickstart for a complete curl example. Key request fields:
  • provider — clone engine version (V1–V5); see Supported clone methods
  • language.target — locale from Supported languages
  • data[] — up to 50 lines; each needs text and voiceId (or timbreRefAudio)
  • outputFormat — wav, mp3, or m4a

​
Workflow (async)

  1. Configure Webhooks
  2. POST to create-async with idempotency key
  3. Handle audio URLs in webhook data.results

​
Voices

  • System voices: POST /openapi/v1/assets/voice/basic/list
  • Cloned voices: create via Voice clone, then use returned voiceId
Full request schema: API reference → TTS operations.