ZeroLabs

# Auth: run `huggingface-cli login` or set HF_TOKEN env var
# Get a token at https://huggingface.co/settings/tokens

# 1. Upload reference audio
UPLOAD_PATH=$(curl -s -X POST \
  "https://k2-fsa-omnivoice.hf.space/gradio_api/upload" \
  -H "Authorization: Bearer $HF_TOKEN" \
  -F "files=@voice.mp3" | jq -r '.[0]')

# 2. Join queue
SESSION=$(uuidgen)
curl -s -X POST \
  "https://k2-fsa-omnivoice.hf.space/gradio_api/queue/join" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $HF_TOKEN" \
  -d '{
    "data": ["Your text here", "English",
      {"path": "'$UPLOAD_PATH'",
       "meta": {"_type": "gradio.FileData"},
       "orig_name": "voice.mp3"},
      "", "", 32, 2.0, true, 1.0, 0, true, true],
    "fn_index": 0,
    "session_hash": "'$SESSION'"
  }'

# 3. Stream result
curl -N \
  "https://k2-fsa-omnivoice.hf.space/gradio_api/queue/data?session_hash=$SESSION" \
  -H "Authorization: Bearer $HF_TOKEN"

// Auth: set TOKEN to your HF token from https://huggingface.co/settings/tokens
const TOKEN = process.env.HF_TOKEN || "hf_...";
const BASE = "https://k2-fsa-omnivoice.hf.space/gradio_api";
const SESSION = crypto.randomUUID();

// 1. Upload
const form = new FormData();
form.append("files", audioFile);
const [path] = await fetch(`${BASE}/upload`, {
  method: "POST",
  headers: { Authorization: `Bearer ${TOKEN}` },
  body: form
}).then(r => r.json());

// 2. Join queue
await fetch(`${BASE}/queue/join`, {
  method: "POST",
  headers: { "Content-Type": "application/json",
    Authorization: `Bearer ${TOKEN}` },
  body: JSON.stringify({
    data: ["Text", "English",
      { path, meta: { _type: "gradio.FileData" },
        orig_name: "voice.mp3" },
      "", "", 32, 2.0, true, 1.0, 0, true, true],
    fn_index: 0, session_hash: SESSION })
});

// 3. Stream SSE
const r = await fetch(
  `${BASE}/queue/data?session_hash=${SESSION}`,
  { headers: { Authorization: `Bearer ${TOKEN}` } }
);

# Auth: run `huggingface-cli login` or set HF_TOKEN env var
# Get a token at https://huggingface.co/settings/tokens
from gradio_client import Client, handle_file

client = Client("k2-fsa/OmniVoice")
result = client.predict(
    text="Your text here",
    lang="English",
    ref_aud=handle_file("voice.mp3"),
    ref_text="", instruct="",
    ns=32, gs=2.0, dn=True,
    sp=1.0, du=0, pp=True, po=True,
    api_name="/_clone_fn"
)
print(result)