Actions28
- Video Actions
- Series Actions
- Image Actions
- Audio Actions
- Voice Actions
- Music Actions
- Connection Actions
- Credits Actions
- Webhook Actions
Audio → Create Speech
AI-generatedSummary
Generate text-to-speech audio using the selected ShortGenius voice. The request runs asynchronously by default; enable Wait for Generation to wait for audio generation to finish before returning.
Inputs
- Text (required) — Text to synthesize into speech.
- Voice ID (required) — Voice to narrate with; use the Voice: List operation to find voice IDs.
- Locale — Optional locale for the speech, such as en-US.
- Wait for Generation — Whether to wait for audio generation to finish before returning; defaults to false.
Output shape
One or more n8n items containing the API response as JSON.
The operation sends a POST request to ShortGenius's speech endpoint. The returned response is emitted as a single item unless it is an array, in which case each array entry becomes a separate item.