Transcriptions API

export PRIME_API_KEY="your-api-key"

curl https://api.pinference.ai/api/v1/audio/transcriptions \
  -H "Authorization: Bearer $PRIME_API_KEY" \
  -F model=qwen/qwen3-asr-1.7b \
  -F file=@meeting.wav

{
  "text": "The quick brown fox jumps over the lazy dog. Prime inference transcribes this clip.",
  "usage": {"type": "duration", "seconds": 4.86925}
}

import base64
import os
import requests

with open("meeting.wav", "rb") as f:
    audio = base64.b64encode(f.read()).decode()

response = requests.post(
    "https://api.pinference.ai/api/v1/audio/transcriptions",
    headers={"Authorization": f"Bearer {os.environ['PRIME_API_KEY']}"},
    json={
        "model": "qwen/qwen3-asr-1.7b",
        "input_audio": {"data": audio, "format": "wav"},
    },
    timeout=600,
)
response.raise_for_status()
print(response.json()["text"])

{
  "task": "transcribe",
  "language": "en",
  "duration": 4.86925,
  "text": "The quick brown fox jumps over the lazy dog. Prime inference transcribes this clip.",
  "segments": [
    {"id": 0, "start": 0, "end": 4.8, "text": "The quick brown fox jumps over the lazy dog. Prime inference transcribes this clip."}
  ],
  "words": [
    {"word": "The", "start": 0, "end": 0.08},
    {"word": "quick", "start": 0.08, "end": 0.32},
    {"word": "brown", "start": 0.4, "end": 0.72}
  ],
  "usage": {"type": "duration", "seconds": 4.86925}
}