Whisper

Model

OpenAI's open-source speech recognition model that runs on your machine

Fiyat: Free, open source
Erişim: None, runs locally

Repo
Model card

Hakkında

Whisper is OpenAI's MIT-licensed speech recognition model and Python package. It transcribes speech in many languages, translates it into English and detects the language, fully offline. It needs ffmpeg, and the large model wants about 10 GB of GPU memory.

Neler yapabilirsin

Transcribe audio files offline on your own machine or server
Translate speech in other languages into English text
Generate SRT or VTT subtitles from video or podcast audio

Başlarken

Install ffmpeg, e.g. brew install ffmpeg
Install the package with pip install -U openai-whisper

Örnek kod

import whisper

model = whisper.load_model("turbo")
result = model.transcribe("audio.mp3")
print(result["text"])

Ayrıntılar

Barındırma: Kendi sunucunda, Kendi bilgisayarında
Kullanılabildiği yerler: Tüm dünya
Resmi SDK'lar: Python
MCP sunucusu: Yok