fish-audio-tts
Generates expressive multilingual text-to-speech narration using fish.audio models with support for cloned voices and inline emotion tags.
What it does
Generate expressive, multilingual narration with fish.audio (S1 / S2-generation models) and reuse cloned voices via reference_id. Use when the user prefers fish.audio/Fish Audio TTS, wants a specific playground voice model, or needs high-emotion voice-clone narration.
Quality judgment
A thorough, well-organized skill covering API mechanics, model selection with cost caveats, emotion tags, tuning parameters, a sample-approval workflow, troubleshooting, and key safety. Minor deductions for tight coupling to OpenMontage-specific tooling (TTSSelector/FishAudioTTS) that limits portability, and some details (promo dates, pricing) that will age.