{
 "name": "Mellotron (expressive TTS)",
 "slug": "mellotron-expressive-tts",
 "category": "text-to-speech",
 "description": "Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data",
 "url": "https://github.com/NVIDIA/mellotron",
 "docs_url": "https://github.com/NVIDIA/mellotron",
 "auth": "none",
 "pricing": "free",
 "http_status": null,
 "last_checked_at": "2026-10-14",
 "status": "active",
 "category_name": "Text-to-Speech",
 "swarmnest_url": "https://swarmnest.ai/directory/text-to-speech/mellotron-expressive-tts/"
}