torch-harmonics
Don’t want to install torch-harmonics? 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.
Spherical signal transforms — used in advanced ASR research.
Best for research workloads adapting spherical transforms to speech. Pricing: free.
What it is
NVIDIA's library for differentiable spherical harmonics. BSD-3-Clause.
Watch out for: Niche; not an ASR engine.
Install / use
pip install torch-harmonicsWhat people actually do with torch-harmonics-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
torch-harmonics vs Whipscribe
| Feature | torch-harmonics | 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 torch-harmonics
Frequently asked about torch-harmonics
Is torch-harmonics free?
Yes. torch-harmonics is free and open source.
Does torch-harmonics work on Mac, Windows and Linux?
torch-harmonics runs on Linux. It is not listed for other platforms; check the vendor for anything beyond Linux.
How do I install torch-harmonics?
With pip: `pip install torch-harmonics`. You need Python and, for most audio tools, ffmpeg on your PATH first.
How many languages does torch-harmonics support?
torch-harmonics lists 1 languages.
Does torch-harmonics identify different speakers?
No. torch-harmonics 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 torch-harmonics give word-level timestamps?
Yes — torch-harmonics produces timing per word, which is what subtitle cues and clip boundaries need.
Can torch-harmonics transcribe live audio?
No — torch-harmonics works on finished files, not a live stream.
Is torch-harmonics HIPAA compliant?
torch-harmonics 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 torch-harmonics?
Niche; not an ASR engine.
Who is torch-harmonics best for?
Research workloads adapting spherical transforms to speech.
Does torch-harmonics run offline?
torch-harmonics runs on your own machine — it is open source, so nothing leaves the computer unless you configure it to.
Can I use torch-harmonics in the browser?
No — torch-harmonics is a Linux application, not a web app. You install it rather than sign in to it.
Where is the torch-harmonics source code?
On GitHub at github.com/NVIDIA/torch-harmonics. It is maintained by NVIDIA.
What kind of tool is torch-harmonics?
In this directory torch-harmonics is filed under research, math, nvidia as a open-source tool.
What are the alternatives to torch-harmonics?
There is a side-by-side page at /tools/torch-harmonics-alternatives comparing torch-harmonics 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 torch-harmonics 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 transcribing a long MP3 or M4A, transcribing a podcast episode and the SRT generator.
Rather have it done for you?
Free tools cost setup time. When you want a finished transcript instead: see an honest roundup of the best transcription services, the cheapest way to transcribe an hour of audio and our transcription service with prices and turnaround.