OpenAI

Whisper

Powerful speech recognition model supporting multilingual transcription and translation

Category Audio Model ID whisper-1

Language Support99+ languages

Model TypeAutomatic Speech Recognition (ASR)

Input Formatmp3, mp4, wav, m4a, etc.

Pricing & Specs

💰 Pricing

Price$0.006 / minute

⚙️ Specs

Language Support99+ languages

Model TypeAutomatic Speech Recognition (ASR)

Input Formatmp3, mp4, wav, m4a, etc.

Max File Size25MB

API Examples

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.zairouter.com/v1",
    api_key="your-api-key"
)

audio_file = open("audio.mp3", "rb")
transcript = client.audio.transcriptions.create(
    model="whisper-1",
    file=audio_file,
    language="zh"  # Optional: specify language
)

print(transcript.text)

cURL

curl https://api.zairouter.com/v1/audio/transcriptions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F file="@audio.mp3" \
  -F model="whisper-1" \
  -F language="zh"

Model Features

Whisper is OpenAI's advanced speech recognition model, supporting multilingual and multi-task capabilities:

Multilingual Support: Recognizes and transcribes 99+ languages
High Accuracy: Maintains high accuracy across various audio quality conditions
Speech Translation: Directly translates foreign language audio to English
Strong Robustness: Can handle background noise and accents

Use Cases

Meeting recording and transcription
Subtitle generation
Voice content analysis
Multilingual translation
Voice assistants

Performance Advantages

Whisper maintains excellent recognition accuracy across various languages and audio quality conditions, making it the preferred solution for speech-to-text conversion.

← Back to Models