Whisper Large V3 Serverless API

 1# pip install "segmind>=1.1.0"
 2# export SEGMIND_API_KEY="YOUR_API_KEY"
 3import segmind
 4
 5# Async (v2): submit to the queue and block until COMPLETED.
 6# run() returns the final result dict (600s deadline, 1.0s poll by default).
 7result = segmind.run(
 8    "whisper-large-v3",
 9    audio_url="https://segmind-resources.s3.amazonaws.com/input/whisper-large-v3-input.mp3",
10    task="transcribe",
11    language="en",
12    max_segment_len=29,
13    merge_chunks=True,
14)
15print(result["status"])                      # COMPLETED
16print(result.get("output"))                  # model output (e.g. media URL)
17print(result["metrics"]["inference_time"])   # server compute seconds
18
19# --- Or submit + poll manually (track request_id, control the cadence) ---
20from segmind import SegmindClient, InferenceFailed, InferenceTimeout
21
22client = SegmindClient()                      # reads SEGMIND_API_KEY
23payload = {
24    "audio_url": "https://segmind-resources.s3.amazonaws.com/input/whisper-large-v3-input.mp3",
25    "task": "transcribe",
26    "language": "en",
27    "max_segment_len": 29,
28    "merge_chunks": True,
29}
30job = client.submit_async("whisper-large-v3", **payload)
31print(job.request_id)                         # available immediately
32try:
33    result = job.wait(timeout=600, interval=1.0)
34except InferenceTimeout as e:
35    print("still running:", e.request_id)
36except InferenceFailed as e:
37    print("failed:", e.detail)