NVIDIA Tacotron2
Don’t want to install NVIDIA Tacotron2? Drop the file here.
The first 20 minutes of any recording are transcribed free: a recording up to 20 minutes transcribes in full, a longer one is previewed, and a pack from $6 (500 minutes) transcribes the rest and opens every export, and credits never expire.
Reference Tacotron2 + WaveGlow stack from NVIDIA.
Best for educational reference for autoregressive TTS. Pricing: free.
What it is
The original NVIDIA Tacotron2 implementation. BSD-3-Clause.
Watch out for: Superseded by FastPitch / Riva TTS.
Install / use
git clone https://github.com/NVIDIA/tacotron2What people actually do with NVIDIA Tacotron2-style transcription
The tool is the means. These are the jobs — each one priced at published rates, each one wired up on its own page.
Features
| Speaker diarization | No |
| Word-level timestamps | Yes |
| Streaming / real-time | No |
| Languages supported | 1 |
| HIPAA eligible | No |
Links
NVIDIA Tacotron2 vs Whipscribe
| Feature | NVIDIA Tacotron2 | Whipscribe |
|---|---|---|
| Category | Open source | Transcription APIs |
| Pricing | free | $6–$24 one-time packs (credits never expire) · first 20 minutes free |
| Speaker identification | No | Named in the summary, key quotes and chapters |
| Word timestamps | Yes | Yes |
| Streaming | No | No |
| Languages | 1 | 99 |
| Platforms | Linux | Web, API, MCP |
Alternatives to NVIDIA Tacotron2
Frequently asked about NVIDIA Tacotron2
Is NVIDIA Tacotron2 free?
Yes. NVIDIA Tacotron2 is free and open source.
Does NVIDIA Tacotron2 work on Mac, Windows and Linux?
NVIDIA Tacotron2 runs on Linux. It is not listed for other platforms; check the vendor for anything beyond Linux.
How do I install NVIDIA Tacotron2?
Clone and run it from source: `git clone https://github.com/NVIDIA/tacotron2`. Expect to install its dependencies yourself — the README has the exact steps per OS.
How many languages does NVIDIA Tacotron2 support?
NVIDIA Tacotron2 lists 1 languages.
Does NVIDIA Tacotron2 identify different speakers?
No. NVIDIA Tacotron2 does not label speakers; a conversation comes back as one continuous text. If you need speaker labels, that is a separate tool or a different service.
Does NVIDIA Tacotron2 give word-level timestamps?
Yes — NVIDIA Tacotron2 produces timing per word, which is what subtitle cues and clip boundaries need.
Can NVIDIA Tacotron2 transcribe live audio?
No — NVIDIA Tacotron2 works on finished files, not a live stream.
Is NVIDIA Tacotron2 HIPAA compliant?
NVIDIA Tacotron2 does not claim HIPAA compliance. For PHI, run it on infrastructure you control or choose a service that will sign a BAA.
What are the limitations of NVIDIA Tacotron2?
Superseded by FastPitch / Riva TTS.
Who is NVIDIA Tacotron2 best for?
Educational reference for autoregressive TTS.
Does NVIDIA Tacotron2 run offline?
NVIDIA Tacotron2 runs on your own machine — it is open source, so nothing leaves the computer unless you configure it to.
Can I use NVIDIA Tacotron2 in the browser?
No — NVIDIA Tacotron2 is a Linux application, not a web app. You install it rather than sign in to it.
Where is the NVIDIA Tacotron2 source code?
On GitHub at github.com/NVIDIA/tacotron2.
What kind of tool is NVIDIA Tacotron2?
In this directory NVIDIA Tacotron2 is filed under tts, legacy, nvidia as a open-source tool.
What are the alternatives to NVIDIA Tacotron2?
There is a side-by-side page at /tools/nvidia-tacotron2-alternatives comparing NVIDIA Tacotron2 with the closest tools in the same category on price, platform and features.
Whipscribe is a hosted transcription 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.
Transcribe your recordings
Running NVIDIA Tacotron2 yourself? Send the same file here and compare the transcript. Transcribe any language, any recording · Transcription services from $0.29 an hour · Transcribe from any meeting or recording platform · How to transcribe, step by step
Explore
All transcription tools · By language · By platform · By file format · How-to guides · Transcription services · Transcription API · Pricing
Long recording to get through?
One file up to 10 hours, as an upload or a link: see how to transcribe an MP3 of any length, transcribing a podcast episode and the SRT generator.
Comparing tools before you pay?
If you would rather pay a service than run software yourself: see an honest roundup of the best transcription services, affordable transcription priced per hour and how our transcription services work.