@noizai

video-translation downloads videos with subtitles, translates speech to a target language via tts with voice cloning, and replaces the audio track while preserving background sound outside speech segments.

tts converts text into speech audio with dual backends (kokoro local, noiz cloud), timeline-accurate dubbing, voice cloning, and per-segment emotion control. supports multiple output formats and messaging platform integrations.

daily-news-caster chains news-aggregator-skill and tts to produce podcast audio from current events, with a procedural workflow that assumes skill availability and happy-path execution.

chat-with-anyone clones or generates voices from video/image sources for speech synthesis roleplay, with ethical guardrails against impersonation and fraud but lacking actionable implementation detail.

characteristic-voice wraps text-to-speech backends (noiz, kokoro) to inject emotional prosody into agent output. covers credential setup and runtime dependencies but omits actual synthesis steps.

template-skill is a scaffold with placeholder headings but no substantive skill definition, inputs, procedures, or decision logic.