langchain/docs/docs/integrations/tools/google_cloud_texttospeech.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a991a6f8-1897-4f49-a191-ae3bdaeda856",
   "metadata": {},
   "source": [
    "# Google Cloud Text-to-Speech\n",
    "\n",
    ">[Google Cloud Text-to-Speech](https://cloud.google.com/text-to-speech) enables developers to synthesize natural-sounding speech with 100+ voices, available in multiple languages and variants. It applies DeepMind’s groundbreaking research in WaveNet and Google’s powerful neural networks to deliver the highest fidelity possible.\n",
    ">\n",
    ">It supports multiple languages, including English, German, Polish, Spanish, Italian, French, Portuguese, and Hindi.\n",
    "\n",
    "This notebook shows how to interact with the `Google Cloud Text-to-Speech API` to achieve speech synthesis capabilities."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9eeb311e-e1bd-4959-8536-4d267f302eb3",
   "metadata": {},
   "source": [
    "First, you need to set up an Google Cloud project. You can follow the instructions [here](https://cloud.google.com/text-to-speech/docs/before-you-begin)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0a309c0e-5310-4eaa-8af9-bcbc252e45da",
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install --upgrade langchain-google-community[texttospeech]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5b86ad38-ac8a-4f0a-a492-01a6e3090c8c",
   "metadata": {},
   "source": [
    "## Instantiation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "e2efded2-894b-4683-89ed-2a6948913fa9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-09-01T17:47:31.565221Z",
     "iopub.status.busy": "2024-09-01T17:47:31.564804Z",
     "iopub.status.idle": "2024-09-01T17:47:31.570600Z",
     "shell.execute_reply": "2024-09-01T17:47:31.569764Z",
     "shell.execute_reply.started": "2024-09-01T17:47:31.565188Z"
    }
   },
   "outputs": [],
   "source": [
    "from langchain_google_community import TextToSpeechTool"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "434b2454-2bff-484d-822c-4026a9dc1383",
   "metadata": {},
   "source": [
    "## Deprecated GoogleCloudTextToSpeechTool"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "2f57a647-9214-4562-a8cf-f263a15d1f40",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-09-01T17:51:28.763915Z",
     "iopub.status.busy": "2024-09-01T17:51:28.763664Z",
     "iopub.status.idle": "2024-09-01T17:51:28.779073Z",
     "shell.execute_reply": "2024-09-01T17:51:28.778477Z",
     "shell.execute_reply.started": "2024-09-01T17:51:28.763897Z"
    }
   },
   "outputs": [],
   "source": [
    "from langchain_community.tools import GoogleCloudTextToSpeechTool"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a2647bc5-e494-41f9-9f53-4a278ea30cc1",
   "metadata": {},
   "outputs": [],
   "source": [
    "text_to_speak = \"Hello world!\"\n",
    "\n",
    "tts = GoogleCloudTextToSpeechTool()\n",
    "tts.name"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d4613fed-66f0-47c6-be50-7e7670654427",
   "metadata": {},
   "source": [
    "We can generate audio, save it to the temporary file and then play it."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "f1984844-aa75-4f83-9d42-1c8052d87cc0",
   "metadata": {},
   "outputs": [],
   "source": [
    "speech_file = tts.run(text_to_speak)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}