Skip to main content
Browse documentation
Capabilities

Text to Speech

Convert text into lifelike speech.

When text-to-speech is enabled for an organization, choose from the voice, model, and output options exposed by the configured runtime. Availability and usage rules vary by provider and account.

  • Pick a voice_id from the voice library or a custom voice.
  • Choose a model identifier exposed by the configured runtime rather than hard-coding an undocumented MobDial model name.
  • Set output_format (e.g. mp3_44100_128) and stream or save the result.
typescript
// SDK publication is release-gated.
// Use the current API/OpenAPI contract and provider-backed identifiers exposed by your environment.

Machine-readable source: /docs/overview/capabilities/text-to-speech.md

MobBotLearning guide

I’ll help turn the documentation into the next action.

Use the current page as the source, then move directly into the product, API, workflow, or support path that matches what you are trying to accomplish.

Browse all docs