NVIDIA Tacotron2

by NVIDIA

Reference Tacotron2 + WaveGlow stack from NVIDIA.

Looking at NVIDIA Tacotron2? Try this first.

Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min

TL;DR

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

Category
Open source
License
BSD-3-Clause
Stars
★ 5.3k
Last push
2024-06-12
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Watch out for: Superseded by FastPitch / Riva TTS.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

Links

GitHub repo ↗

NVIDIA Tacotron2 vs Whipscribe

FeatureNVIDIA Tacotron2Whipscribe
CategoryOpen sourceTranscription APIs
Pricingfree$4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup
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 ★ 107.0k
whisper.cpp
Georgi Gerganov

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

OSS · MIT ★ 52.8k
faster-whisper
SYSTRAN

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

OSS · MIT ★ 24.8k

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.