Convert short mixed Chinese-English text into MP3 or WAV speech audio files.
npx skills add https://github.com/qq5855144/GitHubM --skill short-text-tts
Please help me install this Agent Skill. Skill: short-text-tts Source: https://github.com/qq5855144/GitHubM/tree/main/.skills/short-text-tts Command: npx skills add https://github.com/qq5855144/GitHubM --skill short-text-tts
This Skill turns short mixed-language text into ready-to-play speech audio, removing the need to build or manage a text-to-speech integration manually.
Generate an MP3 narration for the attached short text and save it as a playable audio file.
High-intent search queries and answers about installing and using this skill.
To convert short text to speech, this Skill generates MP3 or WAV audio files with platform-specific playback handling for web, mini program, and app clients. It manages binary responses and base64 transfer for immediate audio playback.
Text-to-speech supports mixed Chinese-English content under 500 characters for voice notifications. It generates spoken alerts and pronunciation checks, producing ready-to-play audio without manual integration.
Handling binary audio from Baidu TTS requires platform-specific playback logic for Expo app clients. This Skill processes binary responses and base64 transfer, delivering playable MP3 or WAV files directly.
You can generate audio files for pronunciation checks using short text under 500 characters. The Skill converts mixed Chinese-English passages into on-demand voice samples and saves them as playable files.
Platform-managed authentication is required for text-to-speech audio generation when using this Skill. It abstracts the authentication process, allowing you to generate short announcements and voice prompts instantly.
Speech audio may not play correctly due to platform-specific playback logic for web, mini program, and app clients. This Skill handles binary responses and base64 transfer to ensure proper audio streaming across platforms.
Xueheng-LiPolish Chinese text to remove AI-style phrasing and translation artifacts.
XJTLUmediaConvert input text into WAV, MP3, or PCM audio files.
rahulrajaramConvert text responses into audible speech using the Kokoro TTS Python library.
lemonlqfSynthesize speech offline using sherpa-onnx runtime and voice models.
