Home › Directory › Text-to-Speech › Mellotron (expressive TTS)
Mellotron (expressive TTS)
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
Visit Mellotron (expressive TTS)Docs
| Category | Text-to-Speech |
|---|---|
| Authentication | No auth |
| Pricing | Free |
| Website | https://github.com/NVIDIA/mellotron |
| Docs | https://github.com/NVIDIA/mellotron |
| Last checked | 2026-10-14 |
| As JSON | /api/v1/directory/mellotron-expressive-tts.json |
Information is summarised in our own words and may be out of date; check the vendor's site for current terms and prices. Not affiliated with Mellotron (expressive TTS). Suggest a correction.
More in Text-to-Speech
Mozilla TTS
:robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts) - GitHub - mozilla/TTS: :robot: Deep learning for Text to Speech.
eSpeak NG
eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.
MaryTTS
MARY TTS -- an open-source, multilingual text-to-speech synthesis system written in pure java
VITS (Vision‑Transformer based TTS)
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech