Actions75
- AI Actions
- Artifact Actions
- Audit Log Actions
- Chat Actions
- Compliance Pattern Actions
- Dataset Actions
- Dataset Row Actions
- Miscellaneous Actions
- Project Actions
- Reference Actions
- Space Actions
AI → Generate Speech
AI-generatedSummary
Synthesizes the required text into speech using the selected voice and text-to-speech model, then writes the audio to the specified binary field.
Inputs
- Text (required) — Text to synthesize.
- Voice — Voice to use; defaults to Alloy. Options are Alloy, Ash, Ballad, Coral, Echo, Fable, Nova, Onyx, Sage, and Shimmer.
- Put Output File in Field (required) — Binary property name for the generated audio; defaults to
data. - Model — Optional text-to-speech model under Additional Options; defaults to
gpt-4o-mini-tts. Supported models depend on the oneAI instance.
Output shape
A binary audio file attached to the item under the configured binary property name.
The source pack shows only the operation signature, so the precise response metadata and audio format are not established here.