.gitignore

@@ -129,5 +129,4 @@ replay_pid*
 
 # Kotlin Gradle plugin data, see https://kotlinlang.org/docs/whatsnew20.html#new-directory-for-kotlin-data-in-gradle-projects
 .kotlin/
-gcp/
+gcp/
-library

build.gradle.kts

@@ -20,28 +20,31 @@ repositories {
 	mavenCentral()
 }
 
+extra["springCloudGcpVersion"] = "7.1.0"
+extra["springCloudVersion"] = "2025.0.0"
+
 dependencies {
 	implementation("org.springframework.boot:spring-boot-starter-data-jpa")
 	implementation("org.springframework.boot:spring-boot-starter-mail")
 	implementation("org.springframework.boot:spring-boot-starter-validation")
 	implementation("org.springframework.boot:spring-boot-starter-web")
-
 	implementation("com.fasterxml.jackson.module:jackson-module-kotlin")
-	implementation("io.github.oshai:kotlin-logging-jvm:7.0.3")
+	implementation("com.google.cloud:spring-cloud-gcp-starter")
 	implementation("org.jetbrains.kotlin:kotlin-reflect")
-
 	implementation("com.google.cloud:google-cloud-texttospeech:2.68.0")
 	implementation("org.apache.poi:poi:5.4.1")
-	implementation("net.bramp.ffmpeg:ffmpeg:0.8.0")
-
 	runtimeOnly("com.mysql:mysql-connector-j")
-	runtimeOnly("com.h2database:h2")
-
-	testRuntimeOnly("org.junit.platform:junit-platform-launcher")
 	testImplementation("org.springframework.boot:spring-boot-starter-test")
 	testImplementation("org.jetbrains.kotlin:kotlin-test-junit5")
-	testImplementation("io.kotest:kotest-runner-junit5:5.9.1")
+	runtimeOnly("com.h2database:h2")
-	testImplementation("io.kotest.extensions:kotest-extensions-spring:1.3.0")
+	testRuntimeOnly("org.junit.platform:junit-platform-launcher")
+}
+
+dependencyManagement {
+	imports {
+		mavenBom("com.google.cloud:spring-cloud-gcp-dependencies:${property("springCloudGcpVersion")}")
+		mavenBom("org.springframework.cloud:spring-cloud-dependencies:${property("springCloudVersion")}")
+	}
 }
 
 kotlin {

src/main/kotlin/com/sangdol/text_to_speech/ConvertSingleTextRequest.kt

@@ -1,8 +0,0 @@
-package com.sangdol.text_to_speech
-
-data class ConvertSingleTextRequest(
-    val text: String,
-    val type: VoiceType,
-    val speakingRate: Double,
-    val order: Int
-)

src/main/kotlin/com/sangdol/text_to_speech/FfmpegUtils.kt

@@ -1,94 +0,0 @@
-package com.sangdol.text_to_speech
-
-import net.bramp.ffmpeg.FFmpeg
-import net.bramp.ffmpeg.FFmpegExecutor
-import net.bramp.ffmpeg.builder.FFmpegBuilder
-import org.springframework.stereotype.Component
-import java.io.File
-
-private const val FFMPEG_PATH: String = "/opt/homebrew/bin/ffmpeg"
-private const val SILENCE_AUDIO_PATH: String = "library/silences"
-
-private fun convertSilenceAudioFilePath(durationMs: Long) = "$SILENCE_AUDIO_PATH/silence-${durationMs}ms.mp3"
-
-@Component
-class FfmpegUtils(
-    private val ffmpegExecutor: FFmpegExecutor = FFmpegExecutor(FFmpeg(FFMPEG_PATH))
-) {
-
-    fun createSilenceAudio(durationMs: Long) {
-        val durationSeconds = durationMs / 1000.0
-        val outputFile = convertSilenceAudioFilePath(durationMs)
-
-        val command = listOf(
-            FFMPEG_PATH,
-            "-y",
-            "-f", "lavfi",
-            "-i", "anullsrc=r=44100:cl=stereo",
-            "-t", durationSeconds.toString(),
-            "-acodec", "mp3",
-            outputFile
-        )
-
-        val process = ProcessBuilder(command)
-            .redirectErrorStream(true)
-            .start()
-
-        process.inputStream.bufferedReader().forEachLine { println(it) }
-        process.waitFor()
-            .takeUnless { exitCode -> exitCode == 0 }
-            ?: throw RuntimeException("FFmpeg failed with exit code ${process.exitValue()}")
-    }
-
-    fun mergeAudioWithInterval(intervalMs: Long, targetDirectory: String, saveDirectory: String, fileName: String) {
-        val targetDir = File(targetDirectory).also { validateIsValidFileDirectory(it) }
-        val fileNameRegex = """(\d+)(.*)""".toRegex()
-
-        if (intervalMs > 0 && !File(convertSilenceAudioFilePath(intervalMs)).exists()) {
-            createSilenceAudio(intervalMs)
-        }
-
-        val files = targetDir.listFiles().sortedBy { it ->
-            val matchResult: MatchResult = fileNameRegex.find(it.name)
-                ?: throw IllegalStateException("Invalid filename-convention")
-            matchResult.groups[1]!!.value.toInt()
-        }.map { "$it" }
-
-        val inputs = mutableListOf<String>()
-        files.forEachIndexed { idx, file ->
-            inputs.add(file)
-            if (intervalMs > 0L && (idx != files.lastIndex)) {
-                inputs.add("library/silences/silence-${intervalMs}ms.mp3")
-            }
-        }
-
-        val builder = FFmpegBuilder()
-
-        inputs.forEach { filePath -> builder.addInput(filePath) }
-
-        val filterInputs = inputs.indices.joinToString("") { idx -> "[$idx:a]" }
-        val filterComplex = "$filterInputs concat=n=${inputs.size}:v=0:a=1[out]"
-
-        builder.setComplexFilter(filterComplex)
-            .addOutput("$saveDirectory/$fileName")
-            .setAudioCodec("mp3")
-            .addExtraArgs("-map", "[out]")
-            .done()
-
-        ffmpegExecutor.createJob(builder).run()
-    }
-
-    private fun validateIsValidFileDirectory(dir: File) {
-        if (!dir.exists()) {
-            throw IllegalArgumentException("Directory not found: $dir")
-        }
-        if (!dir.isDirectory) {
-            throw IllegalArgumentException("Path is not a directory: $dir")
-        }
-        val fileList = dir.listFiles()
-
-        if (fileList == null || fileList.isEmpty()) {
-            throw IllegalArgumentException("Directory is null or empty: $dir")
-        }
-    }
-}

src/main/kotlin/com/sangdol/text_to_speech/GoogleTtsConfig.kt

@@ -1,44 +0,0 @@
-package com.sangdol.text_to_speech
-
-import com.google.cloud.texttospeech.v1.TextToSpeechClient
-import org.springframework.context.annotation.Bean
-import org.springframework.context.annotation.Configuration
-
-@Configuration
-class GoogleTtsConfig {
-
-    @Bean
-    fun textToSpeechClient(): TextToSpeechClient = TextToSpeechClient.create()
-}
-
-enum class TtsLanguageCode(
-    val code: String
-) {
-    ENGLISH_US("en-US")
-}
-
-sealed interface VoiceType {
-    val identifier: String
-    val name: String
-}
-
-enum class Neural2MaleVoice(
-    override val identifier: String,
-): VoiceType {
-    TYPE_A("en-US-Neural2-A"),
-    TYPE_D("en-US-Neural2-D"),
-    TYPE_I("en-US-Neural2-I"),
-    TYPE_J("en-US-Neural2-J"),
-    ;
-}
-
-enum class Neural2FemaleVoice(
-    override val identifier: String
-): VoiceType {
-    TYPE_C("en-US-Neural2-C"),
-    TYPE_E("en-US-Neural2-E"),
-    TYPE_F("en-US-Neural2-F"),
-    TYPE_G("en-US-Neural2-G"),
-    TYPE_H("en-US-Neural2-H"),
-    ;
-}

src/main/kotlin/com/sangdol/text_to_speech/SampleCreateTestRunner.kt

@@ -1,91 +0,0 @@
-package com.sangdol.text_to_speech
-
-import io.github.oshai.kotlinlogging.KLogger
-import io.github.oshai.kotlinlogging.KotlinLogging
-import org.springframework.boot.CommandLineRunner
-import org.springframework.context.annotation.Profile
-import org.springframework.stereotype.Component
-
-private val log: KLogger = KotlinLogging.logger {}
-
-@Profile("none")
-@Component
-class SampleCreateTestRunner(
-    private val singleTextConverter: SingleTextConverter
-) : CommandLineRunner {
-
-    override fun run(vararg args: String?) {
-        listOf(
-            ConvertSingleTextRequest(
-                text = "Did you find the book you were looking for?",
-                type = Neural2FemaleVoice.TYPE_C,
-                speakingRate = 1.0,
-                order = 1
-            ),
-            ConvertSingleTextRequest(
-                text = "Yes, it’s right here. It’s exactly what I need for my project.",
-                type = Neural2MaleVoice.TYPE_A,
-                speakingRate = 1.0,
-                order = 2
-            ),
-            ConvertSingleTextRequest(
-                text = "Great. Do you need help with anything else?",
-                type = Neural2FemaleVoice.TYPE_E,
-                speakingRate = 1.0,
-                order = 3
-            ),
-            ConvertSingleTextRequest(
-                text = "Could you show me how to use the copy machine?",
-                type = Neural2MaleVoice.TYPE_D,
-                speakingRate = 1.0,
-                order = 4
-            ),
-            ConvertSingleTextRequest(
-                text = "Sure, it’s over there in the corner. Let me guide you.",
-                type = Neural2FemaleVoice.TYPE_F,
-                speakingRate = 1.0,
-                order = 5
-            ),
-        ).forEach {
-            val type: VoiceType = it.type
-            val filePath = "library/sample-scripts-1/${it.order}(${genderString(type)}-${type.name}).mp3"
-            singleTextConverter.convert(it, filePath)
-        }
-
-        listOf(
-            ConvertSingleTextRequest(
-                text = "I want to pick up a new hobby, but I’m not sure what to try.",
-                type = Neural2FemaleVoice.TYPE_C,
-                speakingRate = 1.0,
-                order = 1
-            ),
-            ConvertSingleTextRequest(
-                text = "Have you thought about gardening? ",
-                type = Neural2MaleVoice.TYPE_A,
-                speakingRate = 1.0,
-                order = 2
-            ),
-            ConvertSingleTextRequest(
-                text = "Gardening? I’ve never tried it before. What can I grow?",
-                type = Neural2FemaleVoice.TYPE_E,
-                speakingRate = 1.0,
-                order = 3
-            ),
-            ConvertSingleTextRequest(
-                text = "You can start with some flowers for your balcony.",
-                type = Neural2MaleVoice.TYPE_D,
-                speakingRate = 1.0,
-                order = 4
-            ),
-        ).forEach {
-            val type: VoiceType = it.type
-            val filePath = "library/sample-scripts-1/${it.order}(${genderString(type)}-${type.name}).mp3"
-            singleTextConverter.convert(it, filePath)
-        }
-    }
-
-    private fun genderString(type: VoiceType) = when(type) {
-        is Neural2MaleVoice -> "male"
-        is Neural2FemaleVoice -> "female"
-    }
-}

src/main/kotlin/com/sangdol/text_to_speech/SingleTextConverter.kt

@@ -1,44 +0,0 @@
-package com.sangdol.text_to_speech
-
-import com.google.cloud.texttospeech.v1.*
-import com.google.protobuf.ByteString
-import org.springframework.stereotype.Component
-import java.io.File
-import java.io.FileOutputStream
-
-@Component
-class SingleTextConverter(
-    private val ttsClient: TextToSpeechClient
-) {
-    fun convert(
-        request: ConvertSingleTextRequest,
-        filePath: String,
-        language: TtsLanguageCode = TtsLanguageCode.ENGLISH_US,
-        encodingType: AudioEncoding = AudioEncoding.MP3
-    ) {
-        val synthesisInput = SynthesisInput.newBuilder()
-            .setText(request.text)
-            .build()
-
-        val voiceOptions = VoiceSelectionParams.newBuilder()
-            .setLanguageCode(language.code)
-            .setName(request.type.identifier)
-            .build()
-
-        val audioConfig = AudioConfig.newBuilder()
-            .setAudioEncoding(encodingType)
-            .setSpeakingRate(request.speakingRate)
-            .build()
-
-        val synthesizeResponse: SynthesizeSpeechResponse = ttsClient.synthesizeSpeech(synthesisInput, voiceOptions, audioConfig)
-        val content: ByteString = synthesizeResponse.audioContent
-
-        val file = File(filePath).also {
-            it.parentFile
-                .takeIf { dir -> !dir.exists() }
-                ?.mkdirs()
-        }
-
-        FileOutputStream(file).use { it.write(content.toByteArray()) }
-    }
-}

src/main/kotlin/com/sangdol/text_to_speech/TextToSpeechApplication.kt

@@ -4,8 +4,8 @@ import org.springframework.boot.autoconfigure.SpringBootApplication
 import org.springframework.boot.runApplication
 
 @SpringBootApplication
-class TTSApplication
+class TextToSpeechApplication
 
 fun main(args: Array<String>) {
-	runApplication<TTSApplication>(*args)
+	runApplication<TextToSpeechApplication>(*args)
 }