Skip to content

Commit 3b4d7d8

Browse files
codebase/transcribing-audio-files-with-openai-in-spring-ai [BAEL-9287] (#18510)
* add codebase * add live test * add new module to parent pom * add support to add context * update controller method name
1 parent cfd579b commit 3b4d7d8

File tree

11 files changed

+241
-0
lines changed

11 files changed

+241
-0
lines changed

pom.xml

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -761,6 +761,7 @@
761761
<module>spring-actuator</module>
762762
<module>spring-ai</module>
763763
<module>spring-ai-2</module>
764+
<module>spring-ai-3</module>
764765
<module>spring-aop</module>
765766
<module>spring-aop-2</module>
766767
<module>spring-batch</module>
@@ -1149,6 +1150,7 @@
11491150
<module>spring-actuator</module>
11501151
<module>spring-ai</module>
11511152
<module>spring-ai-2</module>
1153+
<module>spring-ai-3</module>
11521154
<module>spring-aop</module>
11531155
<module>spring-aop-2</module>
11541156
<module>spring-batch</module>

spring-ai-3/pom.xml

Lines changed: 84 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,84 @@
1+
<?xml version="1.0" encoding="UTF-8"?>
2+
<project xmlns="http://maven.apache.org/POM/4.0.0"
3+
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
4+
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
5+
<modelVersion>4.0.0</modelVersion>
6+
<artifactId>spring-ai-3</artifactId>
7+
<version>0.0.1</version>
8+
<packaging>jar</packaging>
9+
<name>spring-ai-3</name>
10+
11+
<parent>
12+
<groupId>com.baeldung</groupId>
13+
<artifactId>parent-boot-3</artifactId>
14+
<version>0.0.1-SNAPSHOT</version>
15+
<relativePath>../parent-boot-3</relativePath>
16+
</parent>
17+
18+
<repositories>
19+
<repository>
20+
<id>spring-milestones</id>
21+
<name>Spring Milestones</name>
22+
<url>https://repo.spring.io/milestone</url>
23+
<snapshots>
24+
<enabled>false</enabled>
25+
</snapshots>
26+
</repository>
27+
</repositories>
28+
29+
<dependencies>
30+
<dependency>
31+
<groupId>org.springframework.boot</groupId>
32+
<artifactId>spring-boot-starter-web</artifactId>
33+
</dependency>
34+
<dependency>
35+
<groupId>org.springframework.ai</groupId>
36+
<artifactId>spring-ai-starter-model-openai</artifactId>
37+
<version>${spring-ai.version}</version>
38+
</dependency>
39+
40+
<!-- Test dependencies -->
41+
<dependency>
42+
<groupId>org.springframework.boot</groupId>
43+
<artifactId>spring-boot-starter-test</artifactId>
44+
<scope>test</scope>
45+
</dependency>
46+
</dependencies>
47+
48+
<profiles>
49+
<profile>
50+
<id>transcribe</id>
51+
<activation>
52+
<activeByDefault>true</activeByDefault>
53+
</activation>
54+
<properties>
55+
<spring.boot.mainclass>com.baeldung.springai.transcribe.Application</spring.boot.mainclass>
56+
</properties>
57+
</profile>
58+
</profiles>
59+
60+
<build>
61+
<plugins>
62+
<plugin>
63+
<groupId>org.springframework.boot</groupId>
64+
<artifactId>spring-boot-maven-plugin</artifactId>
65+
<configuration>
66+
<mainClass>${spring.boot.mainclass}</mainClass>
67+
</configuration>
68+
</plugin>
69+
<plugin>
70+
<groupId>org.apache.maven.plugins</groupId>
71+
<artifactId>maven-compiler-plugin</artifactId>
72+
<configuration>
73+
<release>21</release>
74+
</configuration>
75+
</plugin>
76+
</plugins>
77+
</build>
78+
79+
<properties>
80+
<spring-boot.version>3.4.5</spring-boot.version>
81+
<spring-ai.version>1.0.0-M7</spring-ai.version>
82+
</properties>
83+
84+
</project>
Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,15 @@
1+
package com.baeldung.springai.transcribe;
2+
3+
import org.springframework.boot.SpringApplication;
4+
import org.springframework.boot.autoconfigure.SpringBootApplication;
5+
import org.springframework.context.annotation.PropertySource;
6+
7+
@SpringBootApplication
8+
@PropertySource("classpath:application-transcribe.properties")
9+
class Application {
10+
11+
public static void main(String[] args) {
12+
SpringApplication.run(Application.class, args);
13+
}
14+
15+
}
Lines changed: 30 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,30 @@
1+
package com.baeldung.springai.transcribe;
2+
3+
import org.springframework.ai.audio.transcription.AudioTranscriptionPrompt;
4+
import org.springframework.ai.audio.transcription.AudioTranscriptionResponse;
5+
import org.springframework.ai.openai.OpenAiAudioTranscriptionModel;
6+
import org.springframework.ai.openai.OpenAiAudioTranscriptionOptions;
7+
import org.springframework.stereotype.Service;
8+
9+
@Service
10+
class AudioTranscriber {
11+
12+
private final OpenAiAudioTranscriptionModel openAiAudioTranscriptionModel;
13+
14+
AudioTranscriber(OpenAiAudioTranscriptionModel openAiAudioTranscriptionModel) {
15+
this.openAiAudioTranscriptionModel = openAiAudioTranscriptionModel;
16+
}
17+
18+
TranscriptionResponse transcribe(TranscriptionRequest transcriptionRequest) {
19+
AudioTranscriptionPrompt prompt = new AudioTranscriptionPrompt(
20+
transcriptionRequest.audioFile().getResource(),
21+
OpenAiAudioTranscriptionOptions
22+
.builder()
23+
.prompt(transcriptionRequest.context())
24+
.build()
25+
);
26+
AudioTranscriptionResponse response = openAiAudioTranscriptionModel.call(prompt);
27+
return new TranscriptionResponse(response.getResult().getOutput());
28+
}
29+
30+
}
Lines changed: 28 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,28 @@
1+
package com.baeldung.springai.transcribe;
2+
3+
import org.springframework.http.ResponseEntity;
4+
import org.springframework.web.bind.annotation.PostMapping;
5+
import org.springframework.web.bind.annotation.RequestParam;
6+
import org.springframework.web.bind.annotation.RestController;
7+
import org.springframework.web.multipart.MultipartFile;
8+
9+
@RestController
10+
class TranscriptionController {
11+
12+
private final AudioTranscriber audioTranscriber;
13+
14+
TranscriptionController(AudioTranscriber audioTranscriber) {
15+
this.audioTranscriber = audioTranscriber;
16+
}
17+
18+
@PostMapping("/transcribe")
19+
ResponseEntity<TranscriptionResponse> transcribe(
20+
@RequestParam("audioFile") MultipartFile audioFile,
21+
@RequestParam("context") String context
22+
) {
23+
TranscriptionRequest transcriptionRequest = new TranscriptionRequest(audioFile, context);
24+
TranscriptionResponse response = audioTranscriber.transcribe(transcriptionRequest);
25+
return ResponseEntity.ok(response);
26+
}
27+
28+
}
Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,7 @@
1+
package com.baeldung.springai.transcribe;
2+
3+
import org.springframework.lang.Nullable;
4+
import org.springframework.web.multipart.MultipartFile;
5+
6+
record TranscriptionRequest(MultipartFile audioFile, @Nullable String context) {
7+
}
Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,4 @@
1+
package com.baeldung.springai.transcribe;
2+
3+
record TranscriptionResponse(String transcription) {
4+
}
Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
1+
spring.ai.openai.api-key=${OPENAI_API_KEY}
2+
spring.ai.openai.audio.transcription.options.model=whisper-1
3+
spring.ai.openai.audio.transcription.options.language=en
4+
5+
spring.servlet.multipart.max-file-size=25MB
6+
spring.servlet.multipart.max-request-size=25MB
Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,15 @@
1+
<configuration>
2+
<appender name="CONSOLE" class="ch.qos.logback.core.ConsoleAppender">
3+
<encoder>
4+
<pattern>[%d{yyyy-MM-dd HH:mm:ss}] [%p] [%c{1}] - %m%n</pattern>
5+
</encoder>
6+
</appender>
7+
8+
<root level="INFO">
9+
<appender-ref ref="CONSOLE" />
10+
</root>
11+
12+
<logger name="org.springframework" level="INFO" additivity="false">
13+
<appender-ref ref="CONSOLE" />
14+
</logger>
15+
</configuration>
Lines changed: 50 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,50 @@
1+
package com.baeldung.springai.transcribe;
2+
3+
import org.junit.jupiter.api.Test;
4+
import org.junit.jupiter.api.condition.EnabledIfEnvironmentVariable;
5+
import org.springframework.beans.factory.annotation.Autowired;
6+
import org.springframework.boot.test.context.SpringBootTest;
7+
import org.springframework.core.io.DefaultResourceLoader;
8+
import org.springframework.mock.web.MockMultipartFile;
9+
import org.springframework.web.multipart.MultipartFile;
10+
11+
import java.io.IOException;
12+
13+
import static org.assertj.core.api.AssertionsForClassTypes.assertThat;
14+
15+
@SpringBootTest
16+
@EnabledIfEnvironmentVariable(named = "OPENAI_API_KEY", matches = ".*")
17+
class AudioTranscriberLiveTest {
18+
19+
@Autowired
20+
private AudioTranscriber audioTranscriber;
21+
22+
@Test
23+
void whenTranscribeCalledWithAudioFile_thenCorrectTranscriptionGenerated() throws IOException {
24+
String audioFileName = "baeldung-audio-description.mp3";
25+
MultipartFile audioFile = new MockMultipartFile(
26+
audioFileName,
27+
null,
28+
"image/jpeg",
29+
new DefaultResourceLoader()
30+
.getResource("classpath:audio/" + audioFileName)
31+
.getInputStream()
32+
);
33+
34+
String context = "Short description about Baeldung.";
35+
TranscriptionRequest transcriptionRequest = new TranscriptionRequest(audioFile, context);
36+
TranscriptionResponse response = audioTranscriber.transcribe(transcriptionRequest);
37+
38+
assertThat(response)
39+
.isNotNull()
40+
.hasNoNullFieldsOrProperties();
41+
assertThat(response.transcription())
42+
.isEqualToIgnoringWhitespace("""
43+
Baeldung is a top-notch educational platform that specializes in Java, Spring, and related technologies.
44+
It offers a wealth of tutorials, articles, and courses that help developers master programming concepts.
45+
Known for its clear examples and practical guides, Baeldung is a go-to resource for developers looking
46+
to level up their skills.
47+
""");
48+
}
49+
50+
}

0 commit comments

Comments
 (0)