Short answer: Drop the "Hume AI → Hume Octave TTS" action anywhere in your workflow, map the inputs from upstream nodes, and publish.
Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.
| Field | Type | Required | Description |
|---|---|---|---|
Text text | string | Required | Text (required) |
Voice Name voice_name | string | Optional | e.g. Male English Actor |
Voice Description description | string | Optional | warm, calm, slightly amused |
Speed speed | string | Optional | 0.5 - 2.0 |
{"text": "{{trigger.text}}","voice_name": "e.g. Male English Actor","description": "warm, calm, slightly amused","speed": "0.5 - 2.0"}
{"generations": [{"audio": "<base64>","duration": 3.5,"generation_id": "gen_abc"}]}
Use these fields in downstream nodes for routing, logging, or error handling.
Any of these apps can fire this action as part of a workflow.
Triggered by anything in the catalog. Free tier available. No credit card.