ChatterBox.ipynb

chatterbox.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4",
      "authorship_tag": "ABX9TyPboaFJDtVsDzpj2JXYak5N",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/hathibelagal-dev/9aca4ecc759282756d894cf67f281d16/chatterbox.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install chatterbox-tts"
      ],
      "metadata": {
        "id": "sVKIh-JWvtiz"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "AcJX1QYwvHta"
      },
      "outputs": [],
      "source": [
        "import torchaudio as ta\n",
        "from chatterbox.tts import ChatterboxTTS\n",
        "\n",
        "model = ChatterboxTTS.from_pretrained(device=\"cuda\")"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "prompt = \"\"\"\n",
        "His plan’s mostly channeled through SpaceX, his rocket company. Space is hard, y’know?\n",
        "\"\"\""
      ],
      "metadata": {
        "id": "To13tESSvJFv"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "wav = model.generate(\n",
        "    prompt,\n",
        "    exaggeration=0.6,\n",
        ")\n",
        "ta.save(\"output.wav\", wav, model.sr)"
      ],
      "metadata": {
        "id": "0Cwl4FSyvgGb"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from IPython.display import display, Audio\n",
        "display(Audio(\"output.wav\"))"
      ],
      "metadata": {
        "id": "Gk_UjQHNxTMz"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}