Text-to-Speech (WebSocket)

import json, requests, websocket

BASE_URL = "https://studio.evomlabs.com"
API_KEY = "vc_sk_live_YOUR_KEY"
text = "Xin chào, đây là bài test giọng nói."

# 1. Ask for a short-lived token. It expires in 60 seconds, so open the
#    socket immediately afterwards.
token = requests.post(
    f"{BASE_URL}/api/v1/tts/stream-token",
    headers={"Authorization": f"Bearer {API_KEY}"},
    json={"text_length": len(text)},
).json()["data"]

# 2. Always connect to the ws_url the response returned.
ws = websocket.create_connection(f"{token['ws_url']}?token={token['stream_token']}")
ws.send(json.dumps({"type": "start", "text": text, "language": "vi"}))

pcm = bytearray()
while True:
    frame = ws.recv()
    if isinstance(frame, bytes):
        pcm.extend(frame)          # PCM16 mono at 24 kHz
        continue
    event = json.loads(frame)
    if event["type"] in ("done", "error", "cancelled"):
        break

ws.close()
print("received", len(pcm), "bytes of audio")

// Server to client

{ "type": "start", "mode": "fast", "sample_rate": 24000,
  "format": "pcm16", "channels": 1 }

<binary frame>          // PCM16 mono, about 200 ms per frame

{ "type": "done", "mode": "fast", "audio_url": "/api/tts/file/output.wav",
  "chunks": 12, "ttfb_ms": 480, "duration_ms": 5230 }

{ "type": "error", "message": "Error description" }
{ "type": "cancelled" }