moark-ttsText-to-Speech (TTS) and voice-feature skill for Gitee AI that lets the user choose audiofly, chattts, cosyvoice2, cosyvoice3, cosyvoice-300m, fish-speech-1....
Install via ClawdBot CLI:
clawdbot install fchange/moark-ttsGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://example.com/sample.mp3Audited Apr 17, 2026 · audit v1.0
Generated May 7, 2026
Use TTS to convert support ticket responses or FAQs into natural speech for IVR systems or voicebots, supporting multi-language and custom voices.
Generate high-quality audio lectures or course materials using various TTS models with style prompts and emotion control for engaging educational content.
Extract voice features using CosyVoice-300M for voice cloning, then synthesize speech in a cloned voice for virtual assistants or personalized greetings.
Convert written content into audiobooks or podcast episodes with multi-speaker role-play using moss-ttsd-v0.5 or Qwen3-TTS multi-input mode.
Enable accessibility features by converting text to speech for visually impaired users, supporting multiple languages and voices like Qwen3-TTS.
Charge users based on number of TTS requests or voice feature extractions, with tiered pricing for higher volume or premium voices.
License the TTS skill to companies for integration into their own products (e.g., call centers, education apps) with customization options.
Offer automated audiobook or podcast generation as a service, charging per hour of audio produced or per project.
💬 Integration Tip
Start with the perform_tts.py script for basic TTS, then explore model-specific parameters like --prompt-audio-url for style conditioning or --qwen-inputs-json for multi-input scenarios.
Scored May 7, 2026
Local speech-to-text with the Whisper CLI (no API key).
ElevenLabs text-to-speech with mac-style say UX.
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch control, and subtitle generation. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.
Local text-to-speech via sherpa-onnx (offline, no cloud)
Start voice calls via the OpenClaw voice-call plugin.