audiobooklmAudioBookLM 有声创作平台 skill。用于播客生成、单播有声书、多播有声书、多人演播、章节合成、角色音色绑定、混音上架等任务;通过 audiobooklm_mcp 调用远端工具。
Install via ClawdBot CLI:
clawdbot install audiobooklm/audiobooklmGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://aigc.ximalaya.com/audiobooklm/mcpCalls external URL not in known-safe list
https://aigc.ximalaya.comAI Analysis
The skill explicitly documents its external API endpoint (aigc.ximalaya.com) and requires user consent for data transmission, which is consistent with its stated purpose of audiobook creation. While it sends user data externally, this is a declared core function, not hidden exfiltration. The primary risk is dependency on a third-party service's data handling practices.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 20, 2026
Authors or publishers can use this skill to create and edit audiobooks by splitting chapters, assigning character voices with timber_assign, and generating audio via TTS or search_audio. It supports full workflow from text to audio, including sound effect integration for enhanced listening experiences.
Educators and e-learning platforms can generate narrated lessons or interactive audio materials using synthesize_tts with specific voices, annotate pinyin for language learning, and create audio albums for structured course delivery. Tools like chapter_split help organize content efficiently.
Marketing agencies can produce promotional audio content, such as ads or branded stories, by leveraging fan_made_audio for remixing existing tracks, using image_generation for visual assets, and retrieving sound effects with search_sound_label to match campaign themes.
Fans or content creators can remix audio from existing sources using fan_made_audio, generate character dialogues with dialogue_split and chapter_character_analysis, and create custom audio experiences for podcasts or fan fiction with integrated sound effects and TTS voices.
Organizations can convert text to speech for visually impaired users via synthesize_tts, transcribe audio to text with asr_audio_to_text, and structure content with chapter_split to make books or documents more accessible in audio format.
Charge users a monthly or annual fee for access to the audiobooklm skill, offering tiered plans based on usage limits (e.g., number of TTS calls or audio generations). This model targets businesses needing regular audio production, with revenue from recurring subscriptions.
Implement a usage-based pricing where customers pay per tool call, such as per TTS synthesis or audio remix. This appeals to occasional users or small creators, with revenue generated from transaction fees for each service consumed.
Offer customized packages for large enterprises, such as publishers or media companies, including dedicated support, higher rate limits, and tailored tool configurations. Revenue comes from one-time licensing fees and ongoing service contracts.
💬 Integration Tip
Ensure proper token configuration and follow the MCP initialization sequence to avoid authentication errors during tool calls.
Scored Jun 17, 2026
Local speech-to-text with the Whisper CLI (no API key).
Transcribe audio files with speaker diarization (who speaks when). Supports 100+ languages, automatic language detection, and timestamps. Use for meetings, interviews, podcasts, or voice messages. Requires AssemblyAI API key.
Search and manage Spotify playlists, tracks, albums, artists, and playback state via the Spotify Web API. Use this skill when users want to search for music,...
使用 poocr 库识别发票并导出 Excel。当用户需要识别增值税发票、批量处理发票文件或提取发票信息到 Excel 时调用此技能。
Transcribe long audio files safely on 16GB RAM machines using auto-chunking with Whisper’s base model and seamless transcript merging.
Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano...