full-aigc-skills/coze-skills · Archived

coze-asr

Convert speech audio to text using Coze ASR. Use when you need to transcribe spoken content from a remote audio URL or a local audio file into plain text.

First seen Aug 11, 2026

Installation

$ npx skills add full-aigc-skills/coze-skills --skill coze-asr

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from full-aigc-skills/coze-skills.

npx skills add full-aigc-skills/coze-skills

Browse all from full-aigc-skills/coze-skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 1
License LICENSE
Default branch main
Open issues 0
Status Archived

Skill metadata

Parsed from SKILL.md frontmatter.

Declared agents clawdbot

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,496 B
  • docs SUMMARY.md 170 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 3 installs

SKILL.md

Coze ASR

Transcribe audio from a URL or local file using Coze ASR.

Quick start

node {skillDir}/scripts/asr.mjs --url "https://example.com/audio.mp3"
node {skillDir}/scripts/asr.mjs --file ./recording.mp3

Options

  • --url <url>, -u <url> remote audio URL
  • --file <path>, -f <path> local audio file

Behavior

  • One of --url or --file is required.
  • If both --url and --file are provided, the local file input takes precedence.
  • Local files are read and uploaded as base64 audio content.
  • Supported audio formats follow the SDK/API capability: WAV, MP3, OGG Opus, M4A.
  • Recommended limits from the SDK docs: duration up to 2 hours, size up to 100MB.
  • The CLI prints recognized text, and may also print duration and segments.
  • The CLI does not print full utterances details or raw response payload.
  • This skill does not expose custom headers such as --header, -H, or mock mode.

Notes

  • The skill runtime requires plugins.entries.coze-openclaw-plugin.config.apiKey.
  • {skillDir} means the directory containing this SKILL.md.
  • Local files are read and uploaded as base64 audio content.