NVIDIA Tacotron2

by NVIDIA

Reference Tacotron2 + WaveGlow stack from NVIDIA.

TL;DR

Reference Tacotron2 + WaveGlow stack from NVIDIA.

Best for educational reference for autoregressive TTS. Pricing: free.

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

What it is

The original NVIDIA Tacotron2 implementation. BSD-3-Clause.

Best for: Educational reference for autoregressive TTS.
Watch out for: Superseded by FastPitch / Riva TTS.

Install / use

git clone https://github.com/NVIDIA/tacotron2

Features

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

NVIDIA Tacotron2 vs Whipscribe

FeatureNVIDIA Tacotron2Whipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages199
PlatformsLinuxWeb, API, MCP

Alternatives to NVIDIA Tacotron2

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.