VibeVoice/demo/vibevoice_realtime_colab.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "id": "d1785adb",
      "metadata": {
        "colab_type": "text",
        "id": "view-in-github"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/microsoft/VibeVoice/blob/main/demo/vibevoice_realtime_colab.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "WvIaUJD2y0yU",
      "metadata": {
        "id": "WvIaUJD2y0yU"
      },
      "source": [
        "# VibeVoice-Realtime Colab — T4 Quickstart\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "e8fTKYGx7DZk",
      "metadata": {
        "id": "e8fTKYGx7DZk"
      },
      "source": [
        "## Step 1: Setup Environment"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "4wxJ6QHM-ZOb",
      "metadata": {
        "id": "4wxJ6QHM-ZOb"
      },
      "outputs": [],
      "source": [
        "# Check for T4 GPU\n",
        "import torch\n",
        "if torch.cuda.is_available() and \"T4\" in torch.cuda.get_device_name(0):\n",
        "    print(\"✅ T4 GPU detected\")\n",
        "else:\n",
        "    print(\"\"\"\n",
        "    ⚠️ WARNING: T4 GPU not detected\n",
        "\n",
        "    The recommended runtime for this Colab notebook is \"T4 GPU\".\n",
        "\n",
        "    To change the runtime type:\n",
        "\n",
        "        1. Click on \"Runtime\" in the top navigation menu\n",
        "        2. Click on \"Change runtime type\"\n",
        "        3. Select \"T4 GPU\"\n",
        "        4. Click \"OK\" if a \"Disconnect and delete runtime\" window appears\n",
        "        5. Click on \"Save\"\n",
        "\n",
        "    \"\"\")\n",
        "\n",
        "# Clone the VibeVoice repository\n",
        "![ -d /content/VibeVoice ] || git clone --quiet --branch main --depth 1 https://github.com/microsoft/VibeVoice.git /content/VibeVoice\n",
        "print(\"✅ Cloned VibeVoice repository\")\n",
        "\n",
        "# Install project dependencies\n",
        "!uv pip --quiet install --system -e /content/VibeVoice\n",
        "!wget -q https://github.com/cloudflare/cloudflared/releases/latest/download/cloudflared-linux-amd64 -O cloudflared && chmod +x cloudflared\n",
        "print(\"✅ Installed dependencies\")\n",
        "\n",
        "# Download model\n",
        "from huggingface_hub import snapshot_download\n",
        "snapshot_download(\"microsoft/VibeVoice-Realtime-0.5B\", local_dir=\"/content/models/VibeVoice-Realtime-0.5B\")\n",
        "print(\"✅ Downloaded model: microsoft/VibeVoice-Realtime-0.5B\")\n"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "88c727ab",
      "metadata": {},
      "source": [
        "[Optional] If the download exceeds 1 minute, it is probably stuck. You can: (1) interrupt the execution, (2) log in to Hugging Face, and (3) try download again."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "dec6b870",
      "metadata": {},
      "outputs": [],
      "source": [
        "from huggingface_hub import login\n",
        "login()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "c579654b",
      "metadata": {},
      "outputs": [],
      "source": [
        "snapshot_download(\"microsoft/VibeVoice-Realtime-0.5B\", local_dir=\"/content/models/VibeVoice-Realtime-0.5B\")\n",
        "print(\"✅ Downloaded model: microsoft/VibeVoice-Realtime-0.5B\")"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "dfe30d6f",
      "metadata": {},
      "source": [
        "[Optional] More experimental voices"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "bb33c9ce",
      "metadata": {},
      "outputs": [],
      "source": [
        "!bash /content/VibeVoice/demo/download_experimental_voices.sh"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "pgKlV7153Ifi",
      "metadata": {
        "id": "pgKlV7153Ifi"
      },
      "source": [
        "## Step 2: Launch VibeVoice-Realtime Demo"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "Yc1N9EHswFxA",
      "metadata": {
        "id": "Yc1N9EHswFxA"
      },
      "outputs": [],
      "source": [
        "import subprocess, re, time, threading\n",
        "\n",
        "srv = subprocess.Popen(\n",
        "    \"python /content/VibeVoice/demo/vibevoice_realtime_demo.py --model_path /content/models/VibeVoice-Realtime-0.5B --port 8000\",\n",
        "    shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True, bufsize=1, universal_newlines=True,\n",
        ")\n",
        "cf = subprocess.Popen(\n",
        "    \"./cloudflared tunnel --url http://localhost:8000 --no-autoupdate\",\n",
        "    shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True, bufsize=1, universal_newlines=True,\n",
        ")\n",
        "\n",
        "public_url = None\n",
        "server_ready = False\n",
        "url_pattern  = re.compile(r\"(https://[a-z0-9-]+\\.trycloudflare\\.com)\")\n",
        "\n",
        "def read_srv():\n",
        "    global server_ready\n",
        "    for ln in srv.stdout:\n",
        "        print(ln.strip())\n",
        "        if \"Uvicorn running on\" in ln:\n",
        "            server_ready = True\n",
        "\n",
        "def read_cf():\n",
        "    global public_url\n",
        "    for ln in cf.stdout:\n",
        "        m = url_pattern.search(ln)\n",
        "        if m:\n",
        "            public_url = m.group(1)\n",
        "            break\n",
        "\n",
        "threading.Thread(target=read_srv, daemon=True).start()\n",
        "threading.Thread(target=read_cf,  daemon=True).start()\n",
        "\n",
        "\n",
        "while True:\n",
        "    if server_ready and public_url:\n",
        "        print(f\"✅ Public URL: {public_url}\\n\");\n",
        "        public_url = None\n",
        "    time.sleep(0.25)"
      ]
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "gpuType": "T4",
      "include_colab_link": true,
      "machine_shape": "hm",
      "name": "VibeVoice_Colab.ipynb",
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.10.11"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}