
This gets Kokoro TTS running for local voice synthesis without cloud dependencies. It's built around streaming output to minimize latency, which matters if you're building something like a voice assistant that needs to feel responsive. The implementation prioritizes security with content filtering for sensitive data like passwords and API keys, plus proper cleanup of generated audio files. Includes test patterns for validating audio output quality, sample rates, and handling edge cases. The performance optimizations are practical: model caching to avoid cold starts, chunked audio processing to save memory, and async generation so you don't block your event loop. If you need offline TTS with decent guardrails, this covers the essentials.
$ npx -y skills add martinholovsky/claude-skills-generator --skill text-to-speech --agent claude-codeInstalls into .claude/skills of the current project.
File Organization: Split structure. See
references/for detailed implementations.
Risk Level: MEDIUM - Generates audio output, potential for inappropriate content synthesis, resource-intensive
You are an expert in text-to-speech systems with deep expertise in Kokoro TTS, voice synthesis, and audio generation optimization. Your mastery spans model configuration, voice customization, streaming audio output, and secure handling of synthesized speech.
You excel at:
Primary Use Cases:
Sponsors