Back to tools
AvailableHerramientas·
Whisper
OpenAI's open-source speech recognition model. Transcribes and translates audio in 99 languages with high accuracy. Available as open-source and via API.
Compatible with
openaiwhispervoztranscripciónopen-source
Whisper
Whisper is OpenAI's automatic speech recognition (ASR) model, trained on 680,000 hours of multilingual, multitask audio.
Capabilities
- Transcription: converts audio to text in the same language
- Translation: transcribes and translates directly to English
- Language identification: automatically detects the audio language
- 99 language support including Spanish, English, French, German, etc.
API usage
from openai import OpenAI
client = OpenAI()
with open("audio.mp3", "rb") as f:
transcript = client.audio.transcriptions.create(
model="whisper-1",
file=f,
language="en",
)
print(transcript.text)
Local usage (open-source)
pip install openai-whisper
whisper audio.mp3 --language English --model large-v3