3B Orpheus TTS (0.1) 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    "orpheus-3b-0.1",
 9    text="Today has been... exhausting. <sigh> First, I missed the bus. Then it started pouring rain—of course, I forgot my umbrella. <groan> And just when I thought things couldn’t get worse, I spilled coffee all over my white shirt right before the presentation. <cough> But hey, at least I survived... kind of.",
10    top_p=0.95,
11    voice="dan",
12    temperature=0.6,
13    max_new_tokens=1200,
14    repetition_penalty=1.1,
15)
16print(result["status"])                      # COMPLETED
17print(result.get("output"))                  # model output (e.g. media URL)
18print(result["metrics"]["inference_time"])   # server compute seconds
19
20# --- Or submit + poll manually (track request_id, control the cadence) ---
21from segmind import SegmindClient, InferenceFailed, InferenceTimeout
22
23client = SegmindClient()                      # reads SEGMIND_API_KEY
24payload = {
25    "text": "Today has been... exhausting. <sigh> First, I missed the bus. Then it started pouring rain—of course, I forgot my umbrella. <groan> And just when I thought things couldn’t get worse, I spilled coffee all over my white shirt right before the presentation. <cough> But hey, at least I survived... kind of.",
26    "top_p": 0.95,
27    "voice": "dan",
28    "temperature": 0.6,
29    "max_new_tokens": 1200,
30    "repetition_penalty": 1.1,
31}
32job = client.submit_async("orpheus-3b-0.1", **payload)
33print(job.request_id)                         # available immediately
34try:
35    result = job.wait(timeout=600, interval=1.0)
36except InferenceTimeout as e:
37    print("still running:", e.request_id)
38except InferenceFailed as e:
39    print("failed:", e.detail)