Setup & Installation
npx skills add https://github.com/veniceai/skills --skill venice-audio-speech
https://github.com/veniceai/skills/tree/main/skills/venice-audio-speech
View on GitHubWhat This Skill Does
Converts text to speech through Venice AI's API with nine TTS model families, each with its own voice set. Supports mp3, opus, aac, flac, wav, and pcm output, with optional streaming and emotion styling on select models like Qwen 3.
One API call covers nine model families and dozens of voices, so you skip wiring up separate TTS providers or managing multiple SDKs.
When to use it
- Adding narration tracks to blog posts or documentation pages
- Building voice replies into a chatbot or assistant app
- Generating multilingual audio from translated content using Kokoro voices
- Streaming sentence-by-sentence audio for a low-latency chat UI
- Testing different voice families and emotion presets before picking one for production