WorkflowOperators

Generator

The Operator node that synthesizes speech — where a voice and model are assigned per language.

Family: Operator · type: processing_generator

The Generator is the TTS engine. It assigns a voice and model per language and synthesizes the audio — this is where speech is made, and it’s required in every runnable workflow (Export needs the audio only the Generator produces).

Config

The voice_map maps each language to one or more voice assignments:

1node["config"] = {"voice_map": {"en-us": [
2    {"voice_id": voice.provider_voice_id,     # ⚠ the PROVIDER's voice id
3     "provider": "elevenlabs",
4     "model": "eleven_multilingual_v2"}       # the provider's native model id
5]}}

Workflows that translate into several languages have one voice_map entry per language — each needs its own voice.

Two identifier traps live here:

  1. voice_id is the provider’s voice ID (provider_voice_id on a voice object), not the Onepin voice UUID you see in voices list.
  2. model is the provider’s native model ID (e.g. eleven_multilingual_v2, sonic-2) — not the Onepin catalog model IDs shown on Voices & Models.

Get valid voice + model pairs

Pull the provider catalog to see which models a provider offers and which voices each model supports:

1models = client.providers.list_catalog_provider_models("elevenlabs").data
2voices = client.providers.list_catalog_provider_model_voices(
3    "elevenlabs", "eleven_multilingual_v2").data

Inspect this node

1client.nodes.get_node_detail(node_type="processing_generator").data