Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation.
curl https://api.aigateway.sh/v1/audio/transcriptions \ -H "Authorization: Bearer $AIGATEWAY_API_KEY" \ -F model="openai/whisper-large-v3-turbo" \ -F file="@audio.mp3"
# multipart/form-data — use curl -F or SDK file upload model="openai/whisper-large-v3-turbo" file=@audio.mp3 response_format=json # or "verbose_json", "text", "srt", "vtt" language=en # optional
{
"text": "Hello from AIgateway.",
"language": "en",
"duration": 1.82
}from openai import OpenAI
client = OpenAI(base_url="https://api.aigateway.sh/v1", api_key="sk-aig-...")
with open("audio.mp3", "rb") as f:
r = client.audio.transcriptions.create(model="openai/whisper-large-v3-turbo", file=f)
print(r.text)