Which OpenAI models are supported by this skill?

The skill defaults to gpt-4o-mini-tts-2025-12-15 for optimized performance but also supports tts-1 and tts-1-hd models.

Can I use custom voices with the Speech skill?

Custom voice creation is currently out of scope. The skill uses OpenAI's high-quality built-in voices like Cedar and Marin.

How does it handle long scripts or multiple lines?

The skill includes a batch processing mode that handles multiple prompts via JSONL files and automatically manages character limits and rate throttling.

Is an API key required for this skill?

Yes, you must have a valid OPENAI_API_KEY set in your environment to perform live text-to-speech calls.

AI Speech Generation

Name: AI Speech Generation
Author: plurigrid

byplurigrid

•

Content Management

Generates professional text-to-speech audio for narrations, demos, and accessibility using OpenAI's advanced voice models.

The Speech Generation skill enables Claude to produce high-quality spoken audio directly within your project workflow. By leveraging the OpenAI Audio API and a specialized CLI script, it handles everything from single voiceover clips to large-scale batch processing for IVR systems or accessibility reads. The skill features sophisticated instruction augmentation, allowing you to precisely control voice affect, tone, pacing, and emphasis while maintaining deterministic outputs through organized directory conventions and managed dependencies.