sherpa-onnx

by k2-fsa

Don’t want to install sherpa-onnx? 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.

ONNX-runtime ASR: Whisper, Zipformer, Paraformer on every platform.

Linux, macOS, Windows, iOS, Android, Web  ·  free

TL;DR

Best for cross-platform on-device ASR — Android/iOS/Linux/Web, no Python at runtime. Pricing: free.

Category
Open source
License
Apache-2.0
Stars
★ 14.0k
Last push
2026-08-07
Pricing
free
Platforms
Linux, macOS, Windows, iOS, Android, Web

What it is

ONNX-runtime inference for ASR/TTS/VAD/diarization. Ships Java/Kotlin/Swift/JS/.NET bindings. Apache-2.0.

Best for: Cross-platform on-device ASR — Android/iOS/Linux/Web, no Python at runtime.
Watch out for: ONNX export quality varies per model.

Install / use

pip install sherpa-onnx

What people actually do with sherpa-onnx-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.

Wire it into Amazon S3n8nMake.comGoogle DriveZapierSlack

Features

Speaker diarizationYes
Word-level timestampsYes
Streaming / real-timeYes
Languages supported60
HIPAA eligibleNo

Links

GitHub repo ↗

sherpa-onnx vs Whipscribe

Featuresherpa-onnxWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree$6–$24 one-time packs (credits never expire) · first 20 minutes free
Speaker identificationYesNamed in the summary, key quotes and chapters
Word timestampsYesYes
StreamingYesNo
Languages6099
PlatformsLinux, macOS, Windows, iOS, Android, WebWeb, API, MCP

Alternatives to sherpa-onnx

Frequently asked about sherpa-onnx

Is sherpa-onnx free?

Yes. sherpa-onnx is free and open source.

Does sherpa-onnx work on Mac, Windows and Linux?

sherpa-onnx runs on Linux, macOS, Windows, iOS, Android and Web.

How do I install sherpa-onnx?

With pip: `pip install sherpa-onnx`. You need Python and, for most audio tools, ffmpeg on your PATH first.

How many languages does sherpa-onnx support?

sherpa-onnx lists 60 languages.

Does sherpa-onnx identify different speakers?

Yes — sherpa-onnx has speaker diarization, so a two-person interview comes back with each speaker labelled.

Does sherpa-onnx give word-level timestamps?

Yes — sherpa-onnx produces timing per word, which is what subtitle cues and clip boundaries need.

Can sherpa-onnx transcribe live audio?

Yes — sherpa-onnx supports streaming / live input, not just finished files.

Is sherpa-onnx HIPAA compliant?

sherpa-onnx 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 sherpa-onnx?

ONNX export quality varies per model.

Who is sherpa-onnx best for?

Cross-platform on-device ASR — Android/iOS/Linux/Web, no Python at runtime.

Does sherpa-onnx run offline?

sherpa-onnx runs on your own machine — it is open source, so nothing leaves the computer unless you configure it to.

Where is the sherpa-onnx source code?

On GitHub at github.com/k2-fsa/sherpa-onnx. It is maintained by k2-fsa.

What kind of tool is sherpa-onnx?

In this directory sherpa-onnx is filed under toolkit, edge, onnx as a open-source tool.

What are the alternatives to sherpa-onnx?

There is a side-by-side page at /tools/sherpa-onnx-alternatives comparing sherpa-onnx with the closest tools in the same category on price, platform and features.

Can I automate sherpa-onnx-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.

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

Explore

Long recording to get through?

One file up to 10 hours, as an upload or a link: see MP3 to text for long recordings, how to transcribe a podcast and the SRT generator.

Comparing tools before you pay?

If you would rather pay a service than run software yourself: see the best transcription services side by side, cheap transcription services and the real cost per hour and transcription services from $6.