OpenRouter Text-to-Speech
Generates high-quality speech audio from text using OpenRouter's multi-provider API for narration and voiceovers.
The openrouter-tts skill provides a standardized way for Claude to synthesize speech by leveraging OpenRouter's API, which supports leading models from providers like OpenAI, Voxtral, and Kokoro. It allows developers to easily discover available voices, manage output formats such as MP3 or PCM, and implement advanced features like tone steering and speed adjustment. This skill is ideal for projects requiring automated narration, accessibility features, or integrated voice synthesis without the need to manage multiple provider-specific SDKs.
Key Features
01Single API access to multiple TTS providers including OpenAI and Kokoro
02Dynamic discovery of models and provider-specific voice identifiers
03Ready-to-use drop-in workflows for Bash, Python, and TypeScript
04161 GitHub stars
05Support for MP3 and raw PCM audio output formats
06Advanced parameter control for speed and emotional instructions
Use Cases
01Automating narration for articles, chapters, and long-form content
02Generating diverse voiceovers for multimedia presentations and videos
03Building accessibility tools that read text aloud in real-time