Inworld AI
for LuumenAI
Browse Inworld voices and models, then synthesize, transcribe, or embed on approval
Connect Inworld AI and Luumen can list the voices and models available to your account, check pricing, context limits, and modalities, and pull an unmetered preview before anything is generated. Generating speech, transcribing an audio file, or creating embeddings runs as a previewed step you approve. Luumen authenticates with an API key.
The Inworld AI toolbox
6 tools: 3 read, 3 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadGet Voice PreviewGenerate the provider-selected, unmetered MP3 preview for a voice and return it as a downloadable file.
- ReadList ModelsList Inworld-supported models and the pricing, modality, context, and output limits needed to choose a model.
- ReadList VoicesReturn one page of voices available for preview or speech synthesis, with optional filtering, language selection, and sorting.
- WriteCreate EmbeddingsGenerate one complete embedding vector per input text with an Inworld-hosted embedding model. Approval by default
- WriteSynthesize SpeechSynthesize short text with an Inworld voice and return the complete audio as a downloadable file. Approval by default
- WriteTranscribe AudioSynchronously transcribe a short audio file and return the final transcript, timestamps, and usage. Approval by default
One prompt, start to finish
What a governed Inworld AI run looks like inside Luumen.
Questions
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
This connection exposes write actions such as create embeddings, synthesize speech, transcribe audio. For connected tools, admins configure which actions may run automatically and which require approval, within the access granted to the user. Review the configured approval policy before enabling write access.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to Inworld AI — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Often connected alongside
All integrations
Adobe Marketing Agent MCPAdobe Experience Platform context, sandbox switches, and async task status
AffindaRead parsed documents, collections, and annotations — change them with approval
Agent MailGive the agent its own mailbox for reading threads and sending updates
AI/ML APIInspect assistants, threads, and runs — and change them as approved stepsPut Inworld AI to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.