Guia de início rápido: conversão de texto em fala com o Serviço OpenAI do Azure

setx AZURE_OPENAI_API_KEY "REPLACE_WITH_YOUR_KEY_VALUE_HERE" 

setx AZURE_OPENAI_ENDPOINT "REPLACE_WITH_YOUR_ENDPOINT_HERE" 

[System.Environment]::SetEnvironmentVariable('AZURE_OPENAI_API_KEY', 'REPLACE_WITH_YOUR_KEY_VALUE_HERE', 'User')

[System.Environment]::SetEnvironmentVariable('AZURE_OPENAI_ENDPOINT', 'REPLACE_WITH_YOUR_ENDPOINT_HERE', 'User')

echo export AZURE_OPENAI_API_KEY="REPLACE_WITH_YOUR_KEY_VALUE_HERE" >> /etc/environment && source /etc/environment

echo export AZURE_OPENAI_ENDPOINT="REPLACE_WITH_YOUR_ENDPOINT_HERE" >> /etc/environment && source /etc/environment

Saiba mais sobre autenticação sem chave e configuração de variáveis de ambiente.

Saiba mais sobre como localizar chaves de API e definir variáveis de ambiente.

1. Crie um novo arquivo chamado Text-to-speech.js e abra-o no editor de códigos de sua preferência. Copie o seguinte código para o arquivo Text-to-speech.js :

   const { writeFile } = require("fs/promises");
   const { AzureOpenAI } = require("openai");
   const { DefaultAzureCredential, getBearerTokenProvider } = require("@azure/identity");
   require("openai/shims/node");
   
   // You will need to set these environment variables or edit the following values
   const endpoint = process.env["AZURE_OPENAI_ENDPOINT"] || "<endpoint>";
   const speechFilePath = "<path to save the speech file>";
   
   // Required Azure OpenAI deployment name and API version
   const deploymentName = "tts";
   const apiVersion = "2024-08-01-preview";
   
   // keyless authentication    
   const credential = new DefaultAzureCredential();
   const scope = "https://cognitiveservices.azure.com/.default";
   const azureADTokenProvider = getBearerTokenProvider(credential, scope);
   
   function getClient() {
     return new AzureOpenAI({
       endpoint,
       azureADTokenProvider,
       apiVersion,
       deployment: deploymentName,
     });
   }
   
   async function generateAudioStream(
     client,
     params
   ) {
     const response = await client.audio.speech.create(params);
     if (response.ok) return response.body;
     throw new Error(`Failed to generate audio stream: ${response.statusText}`);
   }
   export async function main() {
     console.log("== Text to Speech Sample ==");
   
     const client = getClient();
     const streamToRead = await generateAudioStream(client, {
       model: deploymentName,
       voice: "alloy",
       input: "the quick brown chicken jumped over the lazy dogs",
     });
   
     console.log(`Streaming response to ${speechFilePath}`);
     await writeFile(speechFilePath, streamToRead);
     console.log("Finished streaming");
   }
   
   main().catch((err) => {
     console.error("The sample encountered an error:", err);
   });
   
   

2. Execute o script com o seguinte comando:

   node Text-to-speech.js
   

1. Crie um novo arquivo chamado Text-to-speech.js e abra-o no editor de códigos de sua preferência. Copie o seguinte código para o arquivo Text-to-speech.js :

   const { writeFile } = require("fs/promises");
   const { AzureOpenAI } = require("openai");
   require("openai/shims/node");
   
   // You will need to set these environment variables or edit the following values
   const endpoint = process.env["AZURE_OPENAI_ENDPOINT"] || "<endpoint>";
   const apiKey = process.env["AZURE_OPENAI_API_KEY"] || "<api key>";
   const speechFilePath = "<path to save the speech file>";
   
   // Required Azure OpenAI deployment name and API version
   const deploymentName = "tts";
   const apiVersion = "2024-08-01-preview";
   
   function getClient() {
     return new AzureOpenAI({
       endpoint,
       apiKey,
       apiVersion,
       deployment: deploymentName,
     });
   }
   
   async function generateAudioStream(
     client,
     params
   ) {
     const response = await client.audio.speech.create(params);
     if (response.ok) return response.body;
     throw new Error(`Failed to generate audio stream: ${response.statusText}`);
   }
   export async function main() {
     console.log("== Text to Speech Sample ==");
   
     const client = getClient();
     const streamToRead = await generateAudioStream(client, {
       model: deploymentName,
       voice: "alloy",
       input: "the quick brown chicken jumped over the lazy dogs",
     });
   
     console.log(`Streaming response to ${speechFilePath}`);
     await writeFile(speechFilePath, streamToRead);
     console.log("Finished streaming");
   }
   
   main().catch((err) => {
     console.error("The sample encountered an error:", err);
   });
   
   

2. Execute o script com o seguinte comando:

   node Text-to-speech.js
   

Saiba mais sobre autenticação sem chave e configuração de variáveis de ambiente.

Saiba mais sobre como localizar chaves de API e definir variáveis de ambiente.

1. Crie um novo arquivo chamado Text-to-speech.ts e abra-o em seu editor de código preferido. Copie o seguinte código para o arquivo Text-to-speech.ts :

   import { writeFile } from "fs/promises";
   import { AzureOpenAI } from "openai";
   import { DefaultAzureCredential, getBearerTokenProvider } from "@azure/identity";
   import type { SpeechCreateParams } from "openai/resources/audio/speech";
   import "openai/shims/node";
   
   // You will need to set these environment variables or edit the following values
   const endpoint = process.env["AZURE_OPENAI_ENDPOINT"] || "<endpoint>";
   const speechFilePath = "<path to save the speech file>";
   
   // Required Azure OpenAI deployment name and API version
   const deploymentName = "tts";
   const apiVersion = "2024-08-01-preview";
   
   // keyless authentication    
   const credential = new DefaultAzureCredential();
   const scope = "https://cognitiveservices.azure.com/.default";
   const azureADTokenProvider = getBearerTokenProvider(credential, scope);
   
   function getClient(): AzureOpenAI {
     return new AzureOpenAI({
       endpoint,
       azureADTokenProvider,
       apiVersion,
       deployment: deploymentName,
     });
   }
   
   async function generateAudioStream(
     client: AzureOpenAI,
     params: SpeechCreateParams
   ): Promise<NodeJS.ReadableStream> {
     const response = await client.audio.speech.create(params);
     if (response.ok) return response.body;
     throw new Error(`Failed to generate audio stream: ${response.statusText}`);
   }
   export async function main() {
     console.log("== Text to Speech Sample ==");
   
     const client = getClient();
     const streamToRead = await generateAudioStream(client, {
       model: deploymentName,
       voice: "alloy",
       input: "the quick brown chicken jumped over the lazy dogs",
     });
   
     console.log(`Streaming response to ${speechFilePath}`);
     await writeFile(speechFilePath, streamToRead);
     console.log("Finished streaming");
   }
   
   main().catch((err) => {
     console.error("The sample encountered an error:", err);
   });
   
   

   A importação de é necessária ao executar o código em um ambiente Node.js "openai/shims/node" . Ele garante que o tipo de saída do client.audio.speech.create método esteja corretamente definido como NodeJS.ReadableStream.

2. Crie o aplicativo com o seguinte comando:

   tsc
   

3. Execute o aplicativo com o seguinte comando:

   node Text-to-speech.js
   

1. Crie um novo arquivo chamado Text-to-speech.ts e abra-o em seu editor de código preferido. Copie o seguinte código para o arquivo Text-to-speech.ts :

   import { writeFile } from "fs/promises";
   import { AzureOpenAI } from "openai";
   import type { SpeechCreateParams } from "openai/resources/audio/speech";
   import "openai/shims/node";
   
   // You will need to set these environment variables or edit the following values
   const endpoint = "<endpoint>";
   const apiKey = process.env["AZURE_OPENAI_API_KEY"] || "<api key>";
   const speechFilePath =
     process.env["SPEECH_FILE_PATH"] || "<path to save the speech file>";
   
   // Required Azure OpenAI deployment name and API version
   const deploymentName = "tts";
   const apiVersion = "2024-08-01-preview";
   
   function getClient(): AzureOpenAI {
     return new AzureOpenAI({
       endpoint,
       apiKey,
       apiVersion,
       deployment: deploymentName,
     });
   }
   
   async function generateAudioStream(
     client: AzureOpenAI,
     params: SpeechCreateParams
   ): Promise<NodeJS.ReadableStream> {
     const response = await client.audio.speech.create(params);
     if (response.ok) return response.body;
     throw new Error(`Failed to generate audio stream: ${response.statusText}`);
   }
   export async function main() {
     console.log("== Text to Speech Sample ==");
   
     const client = getClient();
     const streamToRead = await generateAudioStream(client, {
       model: deploymentName,
       voice: "alloy",
       input: "the quick brown chicken jumped over the lazy dogs",
     });
   
     console.log(`Streaming response to ${speechFilePath}`);
     await writeFile(speechFilePath, streamToRead);
     console.log("Finished streaming");
   }
   
   main().catch((err) => {
     console.error("The sample encountered an error:", err);
   });
   
   

   A importação de é necessária ao executar o código em um ambiente Node.js "openai/shims/node" . Ele garante que o tipo de saída do client.audio.speech.create método esteja corretamente definido como NodeJS.ReadableStream.

2. Crie o aplicativo com o seguinte comando:

   tsc
   

3. Execute o aplicativo com o seguinte comando:

   node Text-to-speech.js