Browse skills

This skill automatically reports TTS errors, providing valuable data for identifying and resolving audio generation issues quickly.

Local text-to-speech via sherpa-onnx (offline, no cloud)

Generate realistic, high-quality speech from text using OpenAI's advanced TTS models via Sundial.

Send voice bubble messages to Telegram groups and topics using Microsoft Edge-TTS. Context isolation per topic — different topics use different conversation histories.

Speakturbo TTS allows you to rapidly generate realistic-sounding speech from text, boosting productivity and accessibility for various applications.

This skill converts text to speech (TTS), allowing you to hear your prompts and responses for a more engaging experience.

Edge TTS generates high-quality, low-latency speech from text, ideal for real-time applications and reducing reliance on cloud services.

Zai TTS converts text into natural-sounding speech, offering a quick and easy way to add voiceovers or audio content to your projects.

This skill uses Sherpa and ONNX to convert speech models into TTS formats for efficient deployment and testing – streamlining audio development.