Proof of Use. An independent field guide · No. 01
Back to the collection
Music & Audio

Whisper

Transcribe speech in multiple languages or translate spoken audio into English with OpenAI’s locally runnable speech-recognition models.

transcriptionspeech recognitiontranslationlocal
Source-reviewedNot hands-on testedSources checked

Start with an idea

What you can make

01

Create a reviewable transcript of your own interviews or podcasts

02

Translate permitted non-English recordings into English text

Official examples

See the documented workflow

Creator-supplied notebook linked from the README; example code, not an independently tested live service.

Official multilingual ASR notebook

Before you begin

What it takes to run

Python + FFmpeg

  • Python and PyTorch; README lists expected Python 3.8–3.11 compatibility
  • FFmpeg; Rust may be needed if the tokenizer has no compatible wheel
  • CPU execution is supported; GPU memory depends on model, with README estimates ranging from about 1 GB for tiny/base to 10 GB for large
Runs through / on

Linux · macOS · Windows · Python API · Command line

The real tradeoffs

Cost & licensing

Running costs

No license fee for local inference; you supply the computer or rented compute.

Storage, electricity and cloud GPU time are separate costs. A hosted transcription API is a separate service, not a free entitlement bundled with this repository.

Code license

MIT

Read the code license

Models & other terms

MIT

The actual LICENSE is MIT, and the README explicitly applies it to both code and model weights. Keep required notices; a software license does not supply consent to process recordings.

Know the limitations

  • Can invent or repeat text; verify consequential transcripts against the recording
  • Accuracy varies by language, accent and recording
  • Translation targets English; the turbo model is not trained for translation
  • The model card does not present the base package as real-time transcription out of the box

Follow the evidence

Sources & verification

Official sources were reviewed on October 14, 2026. We did not install, run or benchmark this project. This is a source-check date, not a release date.

Links and project terms can change. These sources document the claims above; they are not a safety certification. Read our full method.

Keep exploring

A few other possibilities

All tools

06Music & Audio

AudioCraft / MusicGen

Explore text- and melody-conditioned music generation with Meta’s AudioCraft research toolkit and MusicGen models.

Try it for

Sketch instrumental musical ideas for noncommercial experimentation

Read entry Official examples
Setup · Advanced
Python + GPU setup
Cost to consider
GPU compute; noncommercial weights

07Music & Audio

Chatterbox

Generate expressive speech from text with Resemble AI’s local text-to-speech family, including multilingual and reference-voice options.

Try it for

Prototype narration or spoken interfaces from your own scripts

Read entry Official examples
Setup · Moderate
Python + model download
Cost to consider
Local or rented compute

08Music & Audio

Demucs

Separate a mixed music recording into vocals, drums, bass and other accompaniment with a locally runnable source-separation model.

Try it for

Isolate parts from your own recordings for practice and analysis

Read entry Official examples
Setup · Moderate
Python + audio dependencies
Cost to consider
Local compute; check weights terms