Loly 3.5 Text-to-Speech API

curl -X POST https://studio.evomlabs.com/api/v1/voices \
  -H "Authorization: Bearer vc_ak_live_YOUR_KEY" \
  -F "file=@sample.wav" \
  -F "name=Authorized sample voice" \
  -F "gender=female" \
  -F "consent=true"

{
  "ok": true,
  "data": {
    "voice_id": "voice_id",
    "name": "Authorized sample voice",
    "status": "ready",
    "deduped": false,
    "gender": "female",
    "description": "",
    "file_name": "sample.wav",
    "file_size": 482310,
    "created_at": "2026-08-03T00:00:00.000Z",
    "key_status": "created",
    "api_key": {
      "key": "vc_sk_live_NEW_KEY",
      "last_four": "ABCD",
      "scopes": ["tts.generate", "tts.stream", "usage.read"]
    }
  }
}

curl -X POST https://studio.evomlabs.com/api/v1/tts/generate \
  -H "Authorization: Bearer vc_sk_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Xin chào, đây là bài test giọng nói.",
    "language": "vi",
    "format": "wav",
    "cfg_value": 2.0,
    "dit_steps": 10
  }'

import requests

BASE_URL = "https://studio.evomlabs.com"
API_KEY = "vc_sk_live_YOUR_KEY"

res = requests.post(
    f"{BASE_URL}/api/v1/tts/generate",
    headers={"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"},
    json={
        "text": "Xin chào, đây là bài test giọng nói.",
        "language": "vi",
        "format": "wav",
    },
)

data = res.json()
if data.get("ok"):
    print("Audio URL:", data["data"]["audio_url"])
else:
    print("Error:", data["error"]["message"])

const BASE_URL = "https://studio.evomlabs.com";
const API_KEY = "vc_sk_live_YOUR_KEY";

const res = await fetch(`${BASE_URL}/api/v1/tts/generate`, {
  method: "POST",
  headers: {
    Authorization: `Bearer ${API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    text: "Xin chào, đây là bài test giọng nói.",
    language: "vi",
    format: "wav",
  }),
});

const { ok, data, error } = await res.json();
if (ok) console.log(data.audio_url);
else console.error(error.message);

{
  "ok": true,
  "data": {
    "success": true,
    "request_id": "cmp3sih7p0002v9o670rd59xc",
    "voice_id": "clx8abc123def",
    "audio_url": "https://cdn.example.com/v1_tts/user123/audio.wav",
    "text": "Xin chào, đây là bài test giọng nói.",
    "duration": null,
    "status": "completed",
    "chars_deducted": 34
  }
}

curl -X POST https://studio.evomlabs.com/api/v1/tts/bytes \
  -H "Authorization: Bearer vc_sk_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"Xin chào","language":"vi","format":"wav"}' \
  --output hello.wav

curl -N -X POST https://studio.evomlabs.com/api/v1/tts/sse \
  -H "Authorization: Bearer vc_sk_live_YOUR_KEY" \
  -H "Accept: text/event-stream" \
  -H "Content-Type: application/json" \
  -d '{"text":"Xin chào","language":"vi"}'

event: start
data: {"sample_rate":24000,"channels":1,"format":"pcm_s16le","encoding":"base64"}

event: audio
data: {"sequence":1,"audio":"<base64 PCM16 little-endian>"}

event: done
data: {"chunks":12,"duration_ms":5230,"elapsed_ms":6100}

curl -X POST https://studio.evomlabs.com/api/v1/tts/stream-token \
  -H "Authorization: Bearer vc_sk_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text_length": 200}'

{
  "ok": true,
  "data": {
    "stream_token": "SHORT_LIVED_TOKEN",
    "ws_url": "wss://studio.evomlabs.com/ws/tts/stream",
    "max_length": 200,
    "chars_deducted": 200,
    "expires_in": 60
  }
}

{
  "type": "start",
  "text": "Xin chào, đây là bài test giọng nói.",
  "language": "vi",
  "speed": 1.0,
  "control_instruction": "",
  "cfg_value": 2.0,
  "dit_steps": 8,
  "use_prompt_text": false,
  "prompt_text": "",
  "do_normalize": false,
  "denoise": true,
  "preprocess_prompt": true,
  "postprocess_output": true
}

// 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" }

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")