domains / families / media / edge-tts

edge-tts

separate

Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch control, and subtitle generation. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.

When to use

• audio/voice output with the "tts" trigger or keyword
• content needs to be spoken rather than read
• specific voice, speed, pitch, or format for TTS output
• subtitle generation
• voice listing
• configuration management for TTS settings

Skill page

Source