HELP CENTER

AI audio

Generate audio for pieces, voiceovers or downloadable resources.

Artificial intelligence

AI audio generation

Description

Generate speech, sound or other supported audio from a prompt through an account-configured AI provider and store the result in Cloud.

When to use it

  • Prepare a voiceover or draft narration.
  • Generate a short sound resource for a multimedia project.
  • Create source audio to arrange and process in Audio Studio.

How to create the service

Open Cloud > New item > AI audio, select the destination, provider and model, and enter the text or prompt expected by that provider. Configure voice, language, format or quality controls when available.

Inputs and configuration

Input requirements vary between text-to-speech and prompt-based audio models. Available parameters can include voice, language, speaking style, duration, sample format and provider-specific controls. Only options shown for the selected model should be assumed.

Processing and status

The request records provider status and account consumption. Short speech may complete directly; longer or generative audio can run asynchronously. A completed provider result must still be persisted successfully before it becomes a Cloud file.

Results and continuity

Save the result in Cloud to play, download, share or add it to Audio Studio and Video Studio. Use Audio Studio for multitrack arrangement, trimming, effects, mixing and format-specific rendering.

Credits and limits

Text length, duration, model, voice and provider pricing can affect cost. Account credits, provider limits, supported languages, storage and maximum duration apply.

Privacy and external processing

Text, prompts and any supported reference audio are processed by the selected provider. Do not clone or imitate a voice without the necessary authorization. Review personal-data, biometric, copyright and disclosure obligations.

Common errors

  • The voice or language is unavailable: select a model that exposes the required combination.
  • The request exceeds a limit: shorten text or duration.
  • The job fails: check provider configuration, policy response and account credits.
  • The audio does not save: verify returned format, storage quota and destination access.

Frequently asked questions

  • Is generated audio public? No. Saved results follow Cloud visibility and remain private by default.
  • Can I edit the result? Yes. Add it to Audio Studio or Video Studio.
  • Can I use any person’s voice? No. Obtain authorization and follow provider and applicable legal requirements.