# Whisper

> Whisper is OpenAI's open speech recognition model in six sizes (39M to 1550M parameters; README lists ~1 GB to ~10 GB VRAM). It transcribes many languages, translates speech to English and identifies the language, via a CLI or Python API. Code and weights are MIT. Install with pip; ffmpeg is required. It does not generate speech, clone voices or run agents.

- Repository: https://github.com/openai/whisper
- Official docs: https://github.com/openai/whisper#readme
- Checked: 2026-10-15

## What it replaces
- ElevenLabs: Speech recognition (full). Local transcription and translation to English; the README does not mention speaker diarization.
- Otter.ai: Meeting transcription (partial). Transcribes recordings locally; no live meeting capture, speaker labels or summaries.

## Facts, with sources

| Question | Status | Answer | Source | Checked |
|---|---|---|---|---|
| Runs on my machine? | Confirmed | Yes, CLI and Python package run on your own machine | https://github.com/openai/whisper#command-line-usage | 2026-10-15 |
| Code licence | Confirmed | MIT | https://github.com/openai/whisper/blob/main/LICENSE | 2026-10-15 |
| Model weights licence | Confirmed | MIT (weights released under the same licence as the code) | https://github.com/openai/whisper#license | 2026-10-15 |
| Commercial use | Confirmed | Yes, MIT code and weights | https://github.com/openai/whisper#license | 2026-10-15 |
| Paid services needed? | Confirmed | None required | https://github.com/openai/whisper#setup | 2026-10-15 |
| Hardware | Confirmed | Required VRAM per model from ~1 GB (tiny, base) to ~10 GB (large); turbo ~6 GB. CPU use is not discussed in the README | https://github.com/openai/whisper#available-models-and-languages | 2026-10-15 |
| Operating systems | Confirmed | README gives ffmpeg install commands for Ubuntu/Debian, Arch, macOS (Homebrew) and Windows (Chocolatey, Scoop) | https://github.com/openai/whisper#setup | 2026-10-15 |
| Setup effort | Confirmed | Easy; pip install openai-whisper plus ffmpeg (Rust may be needed if tiktoken has no prebuilt wheel) | https://github.com/openai/whisper#setup | 2026-10-15 |

GitHub: 110643 stars, 13410 forks, last push 2026-08-31, archived: no.
---
Source: RepoQuarry (https://repoquarry.dev/projects/whisper). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.