Speech-to-text technology has become essential in building transcription services, voice assistants, and accessibility tools. Let us delve into understanding how Spring AI transcribes audio files.<\/p>\n
OpenAI<\/a> provides cutting-edge AI models, including Whisper for speech recognition. Whisper is an automatic speech recognition (ASR) system trained on a large dataset of multilingual and multitask supervised data. It can transcribe audio files into text with impressive accuracy.<\/p>\n To build an application that transcribes audio files using OpenAI with Spring AI, the first step is to set up a Spring Boot project with the correct dependencies and configurations. This ensures that your application can communicate securely and efficiently with the OpenAI API while leveraging the Spring ecosystem. In this section, we\u2019ll walk through initializing the project, adding dependencies, and setting up your configuration files.<\/p>\n Start by creating a new Spring Boot project using Spring Initializr<\/a>. This tool allows you to easily generate a Maven or Gradle project with your selected modules. Include the following dependencies in your project:<\/p>\n Once the project is generated and opened in your IDE (such as IntelliJ or VS Code), add the following dependency to your This starter provides pre-built configurations and components that make it easy to communicate with OpenAI\u2019s API using Spring conventions.<\/p>\n Next, configure your application to securely access the OpenAI API. Open the Replace This section focuses on creating the core functionality that handles the actual transcription of audio files using the OpenAI Whisper model. We’ll implement a REST controller to accept audio input, configure the necessary beans for OpenAI interaction, and enable multipart handling in the application.<\/p>\n The controller is responsible for exposing an endpoint that accepts audio files from the client. It uses the OpenAiAudioApi provided by the Spring AI framework to send the file to OpenAI’s transcription API and return the result to the user. The This code ensures that whenever a user uploads an audio file via POST request, it gets sent to OpenAI for transcription and the resulting text is returned in the response.<\/p>\n To allow Spring to inject and manage the OpenAiAudioApi, we need to configure it as a bean. This configuration class creates a bean using the default OpenAI configuration, which includes your API key and base URL.<\/p>\n The Spring Boot supports file uploads out of the box, but you can customize the maximum file size allowed for upload by adding the following configuration to your `application.yml`. This step is especially useful if users will be uploading large audio files.<\/p>\n This configuration increases the upload limit to 10MB, both for individual files and total request size. You can adjust these values based on your expected file size requirements.<\/p>\n<\/a>2. Setting Up the Spring Boot Project<\/h2>\n
2.1 Project Dependencies<\/h3>\n
\n
@Data<\/code>, @Builder<\/code>, and more.<\/li>\n<\/ul>\npom.xml<\/code> file to enable Spring AI and OpenAI integration:<\/p>\n<dependency>\n <groupId>org.springframework.ai<\/groupId>\n <artifactId>spring-ai-openai-spring-boot-starter<\/artifactId>\n <version>0.8.0-SNAPSHOT<\/version>\n<\/dependency>\n<\/pre>\n
2.2 Configure application.yml<\/h3>\n
src\/main\/resources\/application.yml<\/code> file and add the following configuration:<\/p>\nspring:\n ai:\n openai:\n api-key: YOUR_OPENAI_API_KEY\n base-url: https:\/\/api.openai.com\/v1\n<\/pre>\n
YOUR_OPENAI_API_KEY<\/code> with your actual OpenAI key. You can obtain this key from your OpenAI developer dashboard. The base-url<\/code> is the endpoint for OpenAI\u2019s REST API. This URL is used to make all transcription and model inference requests.<\/a>3. Building the Audio Transcriber<\/h2>\n
3.1 Create Controller<\/h3>\n
@PostMapping<\/code> annotation defines an endpoint \/api\/audio\/transcribe<\/code> that accepts audio data in multipart form. The controller creates a TranscriptionRequest<\/code>, specifying the model as whisper-1<\/code> and the response format as plain text.<\/p>\npackage com.example.transcriber.controller;\n\nimport lombok.RequiredArgsConstructor;\nimport org.springframework.ai.openai.api.OpenAiAudioApi;\nimport org.springframework.ai.openai.api.OpenAiAudioApi.TranscriptionRequest;\nimport org.springframework.http.MediaType;\nimport org.springframework.web.bind.annotation.*;\nimport org.springframework.web.multipart.MultipartFile;\n\nimport java.io.IOException;\n\n@RestController\n@RequiredArgsConstructor\n@RequestMapping(\"\/api\/audio\")\npublic class AudioTranscriptionController {\n\n private final OpenAiAudioApi openAiAudioApi;\n\n @PostMapping(value = \"\/transcribe\", consumes = MediaType.MULTIPART_FORM_DATA_VALUE)\n public String transcribeAudio(@RequestParam(\"file\") MultipartFile file) throws IOException {\n TranscriptionRequest request = TranscriptionRequest.builder()\n .file(file.getResource())\n .model(\"whisper-1\")\n .responseFormat(\"text\")\n .build();\n return openAiAudioApi.transcription(request);\n }\n}\n<\/pre>\n3.2 Enable OpenAiAudioApi as a Bean<\/h3>\n
package com.example.transcriber.config;\n\nimport org.springframework.ai.openai.api.OpenAiAudioApi;\nimport org.springframework.context.annotation.Bean;\nimport org.springframework.context.annotation.Configuration;\nimport org.springframework.web.client.RestClient;\n\n@Configuration\npublic class OpenAIConfig {\n\n @Bean\n public OpenAiAudioApi openAiAudioApi(OpenAiAudioApi.OpenAiAudioApiConfig config) {\n return new OpenAiAudioApi(config, RestClient.builder());\n }\n}\n<\/pre>\nOpenAiAudioApi<\/code> is constructed using its configuration and a RestClient<\/code>. Spring will automatically pick up this bean and inject it wherever needed, such as in the controller class defined earlier.<\/p>\n3.3 Enable Multipart Support<\/h3>\n
spring:\n servlet:\n multipart:\n max-file-size: 10MB\n max-request-size: 10MB\n<\/pre>\n
<\/a>4. Run and Test the Audio Transcriber<\/h2>\n
4.1 Start the Spring Boot App<\/h3>\n