Whisper is OpenAI's speech recognition model — highly accurate transcription in 50+ languages, available via API.

Transcription API

with open("audio.mp3", "rb") as audio_file:
    transcript = client.audio.transcriptions.create(
        model="whisper-1",
        file=audio_file,
        language="en"  # optional, auto-detects if omitted
    )
print(transcript.text)

Translation

# Translate any language to English
translation = client.audio.translations.create(
    model="whisper-1",
    file=audio_file
)

Use Cases

• Meeting transcription, podcast transcripts, voice commands, multilingual customer support

Reference:

Whisper API documentation

https://en.wikipedia.org/wiki/Special:Search?search=Whisper