Transformers.js (xenova mirror)
Don’t want to install Transformers.js? 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.
Original transformers.js repo by Joshua Lochner (pre-merge into HF).
Best for reference checkpoints from the project's pre-HF history. Pricing: free.
What it is
The original transformers.js author's repo, still hosting historical releases. Apache-2.0.
Watch out for: Use huggingface/transformers.js for current work.
Install / use
npm install @xenova/transformersWhat people actually do with Transformers.js (xenova mirror)-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 | Yes |
| Languages supported | 99 |
| HIPAA eligible | No |
Links
Transformers.js (xenova mirror) vs Whipscribe
| Feature | Transformers.js (xenova mirror) | 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 | Yes | No |
| Languages | 99 | 99 |
| Platforms | Web, Node.js | Web, API, MCP |
Alternatives to Transformers.js (xenova mirror)
Frequently asked about Transformers.js (xenova mirror)
Is Transformers.js (xenova mirror) free?
Yes. Transformers.js (xenova mirror) is free and open source.
Does Transformers.js (xenova mirror) work on Mac, Windows and Linux?
Transformers.js (xenova mirror) runs on Web and Node.js. It is not listed for other platforms; check the vendor for anything beyond Web and Node.js.
How many languages does Transformers.js (xenova mirror) support?
Transformers.js (xenova mirror) lists 99 languages. That is the Whisper-family multilingual set, so quality varies by language — English and the large European languages are strongest.
Does Transformers.js (xenova mirror) identify different speakers?
No. Transformers.js (xenova mirror) 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 Transformers.js (xenova mirror) give word-level timestamps?
Yes — Transformers.js (xenova mirror) produces timing per word, which is what subtitle cues and clip boundaries need.
Can Transformers.js (xenova mirror) transcribe live audio?
Yes — Transformers.js (xenova mirror) supports streaming / live input, not just finished files.
Is Transformers.js (xenova mirror) HIPAA compliant?
Transformers.js (xenova mirror) 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 Transformers.js (xenova mirror)?
Use huggingface/transformers.js for current work.
Who is Transformers.js (xenova mirror) best for?
Reference checkpoints from the project's pre-HF history.
Does Transformers.js (xenova mirror) run offline?
Transformers.js (xenova mirror) runs on your own machine — it is open source, so nothing leaves the computer unless you configure it to.
Where is the Transformers.js (xenova mirror) source code?
On GitHub at github.com/xenova/transformers.js. It is maintained by Joshua Lochner.
What kind of tool is Transformers.js (xenova mirror)?
In this directory Transformers.js (xenova mirror) is filed under edge, web, browser as a open-source tool.
What are the alternatives to Transformers.js (xenova mirror)?
There is a side-by-side page at /tools/transformersjs-xenova-alternatives comparing Transformers.js (xenova mirror) with the closest tools in the same category on price, platform and features.
Can I automate Transformers.js (xenova mirror)-style transcription without running it myself?
Yes. If what you want is transcripts rather than the tool itself, Whipscribe does the same job as a hosted API: submit a file or URL, poll a job id, pull the result as txt, json, srt, vtt or docx. $0.012 a minute — about $0.72 an audio hour — bought as credits that never expire. The automation recipes on this site show it wired to Drive folders, Zoom recordings, S3 buckets and no-code platforms.
How is Whipscribe different from Transformers.js (xenova mirror)?
Transformers.js (xenova mirror) is something you run; Whipscribe is something you call. Recordings are transcribed on our own servers and never used for training, and every job returns five formats plus an AI summary, quotes and topics. The first 20 minutes of any recording are transcribed free, and a pack from $6 (500 minutes) transcribes the rest and opens every export.
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 Transformers.js (xenova mirror) 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 MP3 to text for long recordings, transcribing a podcast episode and the SRT generator.
Looking at paid options?
Before you choose a transcription tool or service: see how the best transcription services compare, the cheapest way to transcribe an hour of audio and transcription services from $6.