fish-ttsGenerate high-quality speech from text using Fish Audio S1 and optionally upload the MP3 audio file to NextCloud via WebDAV.
Install via ClawdBot CLI:
clawdbot install gtank1/fish-ttsGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → http://192.168.68.78:7860/v1/audio/speechCalls external URL not in known-safe list
http://192.168.68.78:7860/v1/audio/speechAI Analysis
The skill interacts with local services (Fish Audio S1 and NextCloud) on private IP addresses, which suggests a self-hosted environment. While it sends user text to an external endpoint, the endpoint is local and the skill's purpose is consistent with text-to-speech generation and storage. The primary risk is credential exposure via hardcoded example credentials, not active exfiltration.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 20, 2026
Generate narrated audio for employee training materials, such as compliance courses or software tutorials, using professional voices like em_michael or af_nicole. Upload the audio files to NextCloud for centralized access and distribution across teams, ensuring consistent messaging.
Convert written books or articles into audiobooks with emotional voices like em_alex or af_sarah, applying emotion tags for expressive narration. Store the generated MP3 files on NextCloud for easy sharing with publishers or direct distribution to listeners.
Create clear, natural-sounding voice prompts for interactive voice response (IVR) systems in call centers, using voices like af_rachel for a friendly tone. Upload the audio to NextCloud to integrate with telephony platforms, improving customer experience.
Produce audio lectures or language learning materials with voices tailored to specific languages, such as em_pierre for French or em_marcus for German. Use NextCloud to organize and share these files with students or educational institutions.
Generate high-quality voiceovers for promotional videos or advertisements, selecting voices based on target audience, such as af_bella for warm tones or em_michael for authoritative messages. Upload final audio to NextCloud for collaboration with marketing teams.
Offer a subscription-based platform where users access Fish Audio S1 TTS through a web interface, with tiered plans based on usage limits and voice options. Revenue is generated from monthly or annual fees, targeting businesses needing scalable audio production.
Provide a customized TTS service integrated into enterprise systems, such as CRM or LMS platforms, using this skill for audio generation and NextCloud for storage. Revenue comes from one-time licensing fees and ongoing support contracts.
Deploy an API that allows developers to generate TTS audio on-demand, charging per minute of audio produced. Use this skill for backend processing and NextCloud for file management, with revenue based on usage volume.
💬 Integration Tip
Ensure environment variables for NextCloud and Fish Audio S1 are correctly set before deployment, and test connectivity with the provided troubleshooting commands to avoid common errors.
Scored Apr 19, 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...