Implement speech-to-text (ASR/automatic speech recognition) capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to transcribe audio files, convert speech to text, build voice input features, or process audio recordings. Supports base64 encoded audio files and returns accurate text transcriptions.
Install
npx skills add AnswerZhao/agent-skills --skill ASRnpx skills add AnswerZhao/agent-skills --skill ASR -a claude-code -gnpx skills add AnswerZhao/agent-skills --skill ASR -a codex -ggemini skills install https://github.com/AnswerZhao/agent-skills.git --path glm-skills/ASRgh skill install AnswerZhao/agent-skills ASRgit clone --depth 1 https://github.com/AnswerZhao/agent-skills /tmp/AnswerZhao__agent-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/AnswerZhao__agent-skills/glm-skills/ASR ~/.claude/skills/ASR # Claude Code
cp -R /tmp/AnswerZhao__agent-skills/glm-skills/ASR ~/.agents/skills/ASR # Codex, Cursor, Gemini CLI, Copilot, OpenCode