tts-3Convert text or subtitle files into speech audio with options for voice cloning, emotion control, speed, and timeline-accurate dubbing using Kokoro or Noiz b...
Install via ClawdBot CLI:
clawdbot install Ksuriuri/tts-3Grade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
upload → https://noiz.ai/v1/`Calls external URL not in known-safe list
https://example.com/my_voice.wavUses known external API (expected, informational)
discord.comAI Analysis
The skill's external API calls (Noiz.ai) are consistent with its stated purpose of text-to-speech and voice cloning, and the referenced external audio URL (example.com) is a documented example, not a hidden instruction. However, the 'UNKNOWN_DATA_SINK' signal indicates data is sent to an external endpoint not pre-approved in the skill's permissions, which is a low-risk policy violation but not evidence of malicious exfiltration or credential harvesting.
Generated May 8, 2026
Convert lesson scripts or slide text into natural speech with emotion control using Noiz backend. Ideal for creating multilingual educational content with consistent voice quality and precise timing.
Generate audiobooks from digital documents using Kokoro's native support for chapters. Simple mode handles bulk conversion, while timeline mode enables per-section voice customization for character differentiation.
Translate and dub videos by creating an SRT from original audio, mapping translated segments to voices, and using dynamic reference audio slicing to align new speech with original timestamps. Noiz backend supports emotion and voice cloning.
Generate voice messages in Opus or OGG format for integration with messaging platforms like Telegram or Discord. Simple speak command with format flag enables quick audio responses for conversational agents.
Offer text-to-speech as a cloud API with usage-based pricing. Premium tiers include access to Noiz backend with voice cloning, emotion control, and precise duration features.
Provide a per-project service to convert user-provided EPUB/PDF files into audiobooks with customizable voices. Charge per title or per hour of generated audio.
End-to-end dubbing service for content creators, supporting script translation, voice mapping, and timeline-accurate audio rendering. Revenue from per-minute charges or project-based fees.
💬 Integration Tip
For simple use, start with the basic `speak` command and local Kokoro backend; for advanced features like voice cloning or emotion, set the NOIZ_API_KEY and use the Noiz backend.
Scored May 8, 2026
Audited Apr 16, 2026 · audit v1.0
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.
Secure, offline, OpenAI-compatible local Whisper ASR endpoint for OpenClaw. Features faster-whisper (large-v3-turbo), built-in privacy with no cloud telemetr...
Turn your AI into JARVIS. Voice, wit, and personality — the complete package. Humor cranked to maximum.
Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch contro...
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。