Read-only ElevenLabs catalog brief. It reads account/subscription context, visible voices, model capabilities, and default voice settings through recued-core.elevenlabs, then renders compact tables for choosing a safe voice/model pair. It does not generate audio, download audio, stream output, mutate voices or samples, clone/train voices, configure agents/tools/MCP/secrets, or call arbitrary ElevenLabs routes.

How it works 14 steps

Inspect the data fetches, transforms, gates, and output this recipe runs.

Process (14 steps)

■ user ?

■ subscription ?

■ models_raw ?

■ voices_raw ?

■ default_settings ?

■ models default

Apply default

■ voices default

Apply default

■ model_count count

Count items in models

■ voice_count count

Count items in voices

■ model_rows slice

Take a subset of

■ voice_rows slice

Take a subset of

■ model_table to_table

Format results as a data table

■ voice_table to_table

Format results as a data table

■ card to_summary

Format results as a summary card

Settings 3 configurable

Configurable at install. Defaults shown — change them anytime in Recued.

row limit setting = 20

elevenlabs setting =

show legacy setting = false