ML-SUPERB
Don’t want to install ML-SUPERB? 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.
Multilingual SUPERB — 143 languages × multiple tasks for self-supervised speech models.
Best for probing multilingual self-supervised speech models (XLS-R, MMS, mHuBERT) across LID + ASR. Pricing: free.
What it is
ML-SUPERB is the multilingual extension of SUPERB — 143 languages across language identification and ASR tasks, designed for probing SSL speech encoders. Toolkit: Apache-2.0; component data licenses vary.
Watch out for: Apache-2.0 toolkit · underlying data licenses vary per corpus (Common Voice, MLS, Babel, etc.) · academic-only Babel subset. Cite: Shi et al., Interspeech 2023.
Install / use
git clone https://github.com/s3prl/s3prl # ML-SUPERB benchmark suiteWhat people actually do with ML-SUPERB-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 | No |
| Streaming / real-time | No |
| Languages supported | 143 |
| HIPAA eligible | No |
Links
ML-SUPERB vs Whipscribe
| Feature | ML-SUPERB | 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 | No | Yes |
| Streaming | No | No |
| Languages | 143 | 99 |
| Platforms | GitHub, HuggingFace | Web, API, MCP |
Alternatives to ML-SUPERB
Frequently asked about ML-SUPERB
Is ML-SUPERB free?
Yes. ML-SUPERB is free and open source.
Does ML-SUPERB work on Mac, Windows and Linux?
ML-SUPERB runs on GitHub and HuggingFace. It is not listed for other platforms; check the vendor for anything beyond GitHub and HuggingFace.
How many languages does ML-SUPERB support?
ML-SUPERB lists 143 languages. That is the Whisper-family multilingual set, so quality varies by language — English and the large European languages are strongest.
Does ML-SUPERB identify different speakers?
No. ML-SUPERB 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 ML-SUPERB give word-level timestamps?
No — ML-SUPERB produces segment or sentence timing only, so subtitle cues can land mid-word.
Can ML-SUPERB transcribe live audio?
No — ML-SUPERB works on finished files, not a live stream.
Is ML-SUPERB HIPAA compliant?
ML-SUPERB 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 ML-SUPERB?
Apache-2.0 toolkit · underlying data licenses vary per corpus (Common Voice, MLS, Babel, etc.) · academic-only Babel subset. Cite: Shi et al., Interspeech 2023.
Who is ML-SUPERB best for?
Probing multilingual self-supervised speech models (XLS-R, MMS, mHuBERT) across LID + ASR.
Does ML-SUPERB run offline?
ML-SUPERB runs on your own machine — it is open source, so nothing leaves the computer unless you configure it to.
Can I use ML-SUPERB in the browser?
No — ML-SUPERB is a GitHub and HuggingFace application, not a web app. You install it rather than sign in to it.
Where is the ML-SUPERB source code?
On GitHub at github.com/s3prl/s3prl. It is maintained by Academic consortium (CMU + NTU + JHU + others).
What kind of tool is ML-SUPERB?
In this directory ML-SUPERB is filed under benchmark as a open-source tool.
What are the alternatives to ML-SUPERB?
There is a side-by-side page at /tools/ml-superb-alternatives comparing ML-SUPERB with the closest tools in the same category on price, platform and features.
Can I automate ML-SUPERB-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
Running ML-SUPERB 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
Have the recording already?
Skip the setup and send the file or the link: see transcribing a long MP3 or M4A, a podcast episode as text from its link and an SRT subtitle file from any recording.
Looking at paid options?
Before you choose a transcription tool or service: see the best transcription services side by side, the cheapest way to transcribe an hour of audio and how our transcription services work.