NVIDIA Mellotron

by NVIDIA

Multispeaker prosody TTS — historical NVIDIA release.

TL;DR

Multispeaker prosody TTS — historical NVIDIA release.

Best for reference for prosody-controlled TTS. Pricing: free.

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free
Platforms
Linux

What it is

The Mellotron paper code. BSD-3-Clause.

Best for: Reference for prosody-controlled TTS.
Watch out for: Superseded by Mixer-TTS, FastPitch++.

Install / use

git clone https://github.com/NVIDIA/mellotron

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported1
HIPAA eligibleNo

NVIDIA Mellotron vs Whipscribe

FeatureNVIDIA MellotronWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages199
PlatformsLinuxWeb, API, MCP

Alternatives to NVIDIA Mellotron

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 22.3k

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.