feat: add OpenAI transcribe and TTS models

auto-configurations/models/spring-ai-autoconfigure-model-openai/src/main/java/org/springframework/ai/model/openai/autoconfigure/OpenAiAudioSpeechProperties.java

@@ -36,7 +36,7 @@ public class OpenAiAudioSpeechProperties extends OpenAiParentProperties {
 
 	public static final String CONFIG_PREFIX = "spring.ai.openai.audio.speech";
 
-	public static final String DEFAULT_SPEECH_MODEL = OpenAiAudioApi.TtsModel.TTS_1.getValue();
+	public static final String DEFAULT_SPEECH_MODEL = OpenAiAudioApi.TtsModel.GPT_4_O_MINI_TTS.getValue();
 
 	private static final Float SPEED = 1.0f;
 

auto-configurations/models/spring-ai-autoconfigure-model-openai/src/main/java/org/springframework/ai/model/openai/autoconfigure/OpenAiAudioTranscriptionProperties.java

@@ -26,7 +26,7 @@ public class OpenAiAudioTranscriptionProperties extends OpenAiParentProperties {
 
 	public static final String CONFIG_PREFIX = "spring.ai.openai.audio.transcription";
 
-	public static final String DEFAULT_TRANSCRIPTION_MODEL = OpenAiAudioApi.WhisperModel.WHISPER_1.getValue();
+	public static final String DEFAULT_TRANSCRIPTION_MODEL = OpenAiAudioApi.TranscriptionModels.WHISPER_1.getValue();
 
 	private static final Double DEFAULT_TEMPERATURE = 0.7;
 

models/spring-ai-openai/src/main/java/org/springframework/ai/openai/OpenAiAudioSpeechModel.java

@@ -80,7 +80,7 @@ public class OpenAiAudioSpeechModel implements SpeechModel, StreamingSpeechModel
 	public OpenAiAudioSpeechModel(OpenAiAudioApi audioApi) {
 		this(audioApi,
 				OpenAiAudioSpeechOptions.builder()
-					.model(OpenAiAudioApi.TtsModel.TTS_1.getValue())
+					.model(OpenAiAudioApi.TtsModel.GPT_4_O_MINI_TTS.getValue())
 					.responseFormat(AudioResponseFormat.MP3)
 					.voice(OpenAiAudioApi.SpeechRequest.Voice.ALLOY.getValue())
 					.speed(SPEED)

models/spring-ai-openai/src/main/java/org/springframework/ai/openai/OpenAiAudioTranscriptionModel.java

@@ -63,7 +63,7 @@ public class OpenAiAudioTranscriptionModel implements TranscriptionModel {
 	public OpenAiAudioTranscriptionModel(OpenAiAudioApi audioApi) {
 		this(audioApi,
 				OpenAiAudioTranscriptionOptions.builder()
-					.model(OpenAiAudioApi.WhisperModel.WHISPER_1.getValue())
+					.model(OpenAiAudioApi.TranscriptionModels.WHISPER_1.getValue())
 					.responseFormat(OpenAiAudioApi.TranscriptResponseFormat.JSON)
 					.temperature(0.7f)
 					.build());

models/spring-ai-openai/src/main/java/org/springframework/ai/openai/api/OpenAiAudioApi.java

@@ -27,6 +27,7 @@
 import reactor.core.publisher.Mono;
 
 import org.springframework.ai.model.ApiKey;
+import org.springframework.ai.model.ChatModelDescription;
 import org.springframework.ai.model.NoopApiKey;
 import org.springframework.ai.model.SimpleApiKey;
 import org.springframework.ai.openai.api.common.OpenAiApiConstants;
@@ -50,6 +51,7 @@
  * @author Ilayaperumal Gopinathan
  * @author Jonghoon Park
  * @author Filip Hrisafov
+ * @author Alexandros Pappas
  * @since 0.8.1
  */
 public class OpenAiAudioApi {
@@ -224,18 +226,18 @@ public String getFilename() {
 	 * different model variates, tts-1 is optimized for real time text to speech use cases
 	 * and tts-1-hd is optimized for quality. These models can be used with the Speech
 	 * endpoint in the Audio API. Reference:
-	 * <a href="https://platform.openai.com/docs/models/tts">TTS</a>
+	 * <a href="https://platform.openai.com/docs/models#tts">TTS</a>
 	 */
 	public enum TtsModel {
 
 		// @formatter:off
 		/**
-		 * The latest text to speech model, optimized for speed.
+		 * Text-to-speech model optimized for speed
 		 */
 		@JsonProperty("tts-1")
 		TTS_1("tts-1"),
 		/**
-		 * The latest text to speech model, optimized for quality.
+		 * Text-to-speech model optimized for quality.
 		 */
 		@JsonProperty("tts-1-hd")
 		TTS_1_HD("tts-1-hd"),
@@ -266,6 +268,7 @@ public String getValue() {
 	 * v2-large model is currently available through our API with the whisper-1 model
 	 * name.
 	 */
+	@Deprecated
 	public enum WhisperModel {
 
 		// @formatter:off
@@ -285,6 +288,45 @@ public String getValue() {
 
 	}
 
+	/**
+	 * The available models for the transcriptions API. Reference:
+	 * <a href="https://platform.openai.com/docs/models#transcription">
+	 */
+	public enum TranscriptionModels implements ChatModelDescription {
+
+		/**
+		 * Speech-to-text model powered by GPT-4o
+		 */
+		@JsonProperty("gpt-4o-transcribe")
+		GPT_4O_TRANSCRIBE("gpt-4o-transcribe"),
+		/**
+		 * Speech-to-text model powered by GPT-4o mini
+		 */
+		@JsonProperty("gpt-4o-mini-transcribe")
+		GPT_4O_MINI_TRANSCRIBE("gpt-4o-mini-transcribe"),
+		/**
+		 * General-purpose speech recognition model
+		 */
+		@JsonProperty("whisper-1")
+		WHISPER_1("whisper-1");
+
+		public final String value;
+
+		TranscriptionModels(String value) {
+			this.value = value;
+		}
+
+		public String getValue() {
+			return this.value;
+		}
+
+		@Override
+		public String getName() {
+			return this.value;
+		}
+
+	}
+
 	/**
 	 * The format of the transcript and translation outputs, in one of these options:
 	 * json, text, srt, verbose_json, or vtt. Defaults to json.
@@ -437,7 +479,7 @@ public String getValue() {
 		 */
 		public static class Builder {
 
-			private String model = TtsModel.TTS_1.getValue();
+			private String model = TtsModel.GPT_4_O_MINI_TTS.getValue();
 
 			private String input;
 
@@ -556,7 +598,7 @@ public static class Builder {
 
 			private String fileName;
 
-			private String model = WhisperModel.WHISPER_1.getValue();
+			private String model = TranscriptionModels.WHISPER_1.getValue();
 
 			private String language;
 
@@ -659,7 +701,7 @@ public static class Builder {
 
 			private String fileName;
 
-			private String model = WhisperModel.WHISPER_1.getValue();
+			private String model = TranscriptionModels.WHISPER_1.getValue();
 
 			private String prompt;
 

models/spring-ai-openai/src/test/java/org/springframework/ai/openai/audio/api/OpenAiAudioApiIT.java

@@ -27,10 +27,10 @@
 import org.springframework.ai.openai.api.OpenAiAudioApi.SpeechRequest;
 import org.springframework.ai.openai.api.OpenAiAudioApi.SpeechRequest.Voice;
 import org.springframework.ai.openai.api.OpenAiAudioApi.StructuredResponse;
+import org.springframework.ai.openai.api.OpenAiAudioApi.TranscriptionModels;
 import org.springframework.ai.openai.api.OpenAiAudioApi.TranscriptionRequest;
 import org.springframework.ai.openai.api.OpenAiAudioApi.TranslationRequest;
 import org.springframework.ai.openai.api.OpenAiAudioApi.TtsModel;
-import org.springframework.ai.openai.api.OpenAiAudioApi.WhisperModel;
 import org.springframework.util.FileCopyUtils;
 
 import static org.assertj.core.api.Assertions.assertThat;
@@ -52,7 +52,7 @@ void speechTranscriptionAndTranslation() throws IOException {
 
 		byte[] speech = this.audioApi
 			.createSpeech(SpeechRequest.builder()
-				.model(TtsModel.TTS_1_HD.getValue())
+				.model(TtsModel.GPT_4_O_MINI_TTS.getValue())
 				.input("Hello, my name is Chris and I love Spring A.I.")
 				.voice(Voice.ONYX.getValue())
 				.build())
@@ -64,7 +64,7 @@ void speechTranscriptionAndTranslation() throws IOException {
 
 		StructuredResponse translation = this.audioApi
 			.createTranslation(TranslationRequest.builder()
-				.model(WhisperModel.WHISPER_1.getValue())
+				.model(TranscriptionModels.WHISPER_1.getValue())
 				.file(speech)
 				.fileName("speech.mp3")
 				.build(), StructuredResponse.class)
@@ -74,7 +74,7 @@ void speechTranscriptionAndTranslation() throws IOException {
 
 		StructuredResponse transcriptionEnglish = this.audioApi
 			.createTranscription(TranscriptionRequest.builder()
-				.model(WhisperModel.WHISPER_1.getValue())
+				.model(TranscriptionModels.WHISPER_1.getValue())
 				.file(speech)
 				.fileName("speech.mp3")
 				.build(), StructuredResponse.class)

models/spring-ai-openai/src/test/java/org/springframework/ai/openai/audio/api/OpenAiAudioModelNoOpApiKeysIT.java

@@ -44,7 +44,7 @@ public class OpenAiAudioModelNoOpApiKeysIT {
 	void checkNoOpKey() {
 		assertThatThrownBy(() -> this.audioApi
 			.createSpeech(OpenAiAudioApi.SpeechRequest.builder()
-				.model(OpenAiAudioApi.TtsModel.TTS_1_HD.getValue())
+				.model(OpenAiAudioApi.TtsModel.GPT_4_O_MINI_TTS.getValue())
 				.input("Hello, my name is Chris and I love Spring A.I.")
 				.voice(OpenAiAudioApi.SpeechRequest.Voice.ONYX.getValue())
 				.build())

models/spring-ai-openai/src/test/java/org/springframework/ai/openai/audio/speech/OpenAiSpeechModelIT.java

@@ -64,7 +64,7 @@ void shouldGenerateNonEmptyMp3AudioFromSpeechPrompt() {
 			.voice(OpenAiAudioApi.SpeechRequest.Voice.ALLOY.getValue())
 			.speed(SPEED)
 			.responseFormat(OpenAiAudioApi.SpeechRequest.AudioResponseFormat.MP3)
-			.model(OpenAiAudioApi.TtsModel.TTS_1.value)
+			.model(OpenAiAudioApi.TtsModel.GPT_4_O_MINI_TTS.value)
 			.build();
 		SpeechPrompt speechPrompt = new SpeechPrompt("Today is a wonderful day to build something people love!",
 				speechOptions);
@@ -100,7 +100,7 @@ void speechRateLimitTest() {
 			.voice(OpenAiAudioApi.SpeechRequest.Voice.ALLOY.getValue())
 			.speed(SPEED)
 			.responseFormat(OpenAiAudioApi.SpeechRequest.AudioResponseFormat.MP3)
-			.model(OpenAiAudioApi.TtsModel.TTS_1.value)
+			.model(OpenAiAudioApi.TtsModel.GPT_4_O_MINI_TTS.value)
 			.build();
 		SpeechPrompt speechPrompt = new SpeechPrompt("Today is a wonderful day to build something people love!",
 				speechOptions);
@@ -120,7 +120,7 @@ void shouldStreamNonEmptyResponsesForValidSpeechPrompts() {
 			.voice(OpenAiAudioApi.SpeechRequest.Voice.ALLOY.getValue())
 			.speed(SPEED)
 			.responseFormat(OpenAiAudioApi.SpeechRequest.AudioResponseFormat.MP3)
-			.model(OpenAiAudioApi.TtsModel.TTS_1.value)
+			.model(OpenAiAudioApi.TtsModel.GPT_4_O_MINI_TTS.value)
 			.build();
 
 		SpeechPrompt speechPrompt = new SpeechPrompt("Today is a wonderful day to build something people love!",
@@ -142,7 +142,7 @@ void speechVoicesTest(String voice) {
 			.voice(voice)
 			.speed(SPEED)
 			.responseFormat(OpenAiAudioApi.SpeechRequest.AudioResponseFormat.MP3)
-			.model(OpenAiAudioApi.TtsModel.TTS_1.value)
+			.model(OpenAiAudioApi.TtsModel.GPT_4_O_MINI_TTS.value)
 			.build();
 		SpeechPrompt speechPrompt = new SpeechPrompt("Today is a wonderful day to build something people love!",
 				speechOptions);

models/spring-ai-openai/src/test/java/org/springframework/ai/openai/audio/speech/OpenAiSpeechModelWithSpeechResponseMetadataTests.java

@@ -75,7 +75,7 @@ void aiResponseContainsImageResponseMetadata() {
 			.voice(OpenAiAudioApi.SpeechRequest.Voice.ALLOY.getValue())
 			.speed(SPEED)
 			.responseFormat(OpenAiAudioApi.SpeechRequest.AudioResponseFormat.MP3)
-			.model(OpenAiAudioApi.TtsModel.TTS_1.value)
+			.model(OpenAiAudioApi.TtsModel.GPT_4_O_MINI_TTS.value)
 			.build();
 
 		SpeechPrompt speechPrompt = new SpeechPrompt("Today is a wonderful day to build something people love!",

spring-ai-docs/src/main/antora/modules/ROOT/pages/api/audio/speech/openai-speech.adoc

@@ -85,7 +85,7 @@ The prefix `spring.ai.openai.audio.speech` is used as the property prefix that l
 | spring.ai.openai.audio.speech.api-key    | The API Key           |  -
 | spring.ai.openai.audio.speech.organization-id | Optionally you can specify which organization  used for an API request. |  -
 | spring.ai.openai.audio.speech.project-id      | Optionally, you can specify which project is used for an API request. |  -
-| spring.ai.openai.audio.speech.options.model  | ID of the model to use for generating the audio. For OpenAI's TTS API, use one of the available models: tts-1 or tts-1-hd. |  tts-1
+| spring.ai.openai.audio.speech.options.model  | ID of the model to use for generating the audio. Available models: `gpt-4o-mini-tts` (default, optimized for speed and cost), `gpt-4o-tts` (higher quality), `tts-1` (legacy, optimized for speed), or `tts-1-hd` (legacy, optimized for quality). |  gpt-4o-mini-tts
 | spring.ai.openai.audio.speech.options.voice | The voice to use for synthesis. For OpenAI's TTS API, One of the available voices for the chosen model: alloy, echo, fable, onyx, nova, and shimmer. | alloy
 | spring.ai.openai.audio.speech.options.response-format | The format of the audio output. Supported formats are mp3, opus, aac, flac, wav, and pcm. | mp3
 | spring.ai.openai.audio.speech.options.speed | The speed of the voice synthesis. The acceptable range is from 0.25 (slowest) to 4.0 (fastest). | 1.0
@@ -107,7 +107,7 @@ For example:
 [source,java]
 ----
 OpenAiAudioSpeechOptions speechOptions = OpenAiAudioSpeechOptions.builder()
-    .model("tts-1")
+    .model("gpt-4o-mini-tts")
     .voice(OpenAiAudioApi.SpeechRequest.Voice.ALLOY)
     .responseFormat(OpenAiAudioApi.SpeechRequest.AudioResponseFormat.MP3)
     .speed(1.0f)
@@ -153,7 +153,7 @@ var openAiAudioSpeechModel = new OpenAiAudioSpeechModel(openAiAudioApi);
 var speechOptions = OpenAiAudioSpeechOptions.builder()
     .responseFormat(OpenAiAudioApi.SpeechRequest.AudioResponseFormat.MP3)
     .speed(1.0f)
-    .model(OpenAiAudioApi.TtsModel.TTS_1.value)
+    .model(OpenAiAudioApi.TtsModel.GPT_4_O_MINI_TTS.value)
     .build();
 
 var speechPrompt = new SpeechPrompt("Hello, this is a text-to-speech example.", speechOptions);
@@ -181,7 +181,7 @@ OpenAiAudioSpeechOptions speechOptions = OpenAiAudioSpeechOptions.builder()
     .voice(OpenAiAudioApi.SpeechRequest.Voice.ALLOY)
     .speed(1.0f)
     .responseFormat(OpenAiAudioApi.SpeechRequest.AudioResponseFormat.MP3)
-    .model(OpenAiAudioApi.TtsModel.TTS_1.value)
+    .model(OpenAiAudioApi.TtsModel.GPT_4_O_MINI_TTS.value)
     .build();
 
 SpeechPrompt speechPrompt = new SpeechPrompt("Today is a wonderful day to build something people love!", speechOptions);

spring-ai-docs/src/main/antora/modules/ROOT/pages/api/audio/transcriptions/openai-transcriptions.adoc

@@ -83,7 +83,7 @@ The prefix `spring.ai.openai.audio.transcription` is used as the property prefix
 | spring.ai.openai.audio.transcription.api-key    | The API Key           |  -
 | spring.ai.openai.audio.transcription.organization-id | Optionally you can specify which organization  used for an API request. |  -
 | spring.ai.openai.audio.transcription.project-id      | Optionally, you can specify which project is used for an API request. |  -
-| spring.ai.openai.audio.transcription.options.model  | ID of the model to use. Only whisper-1 (which is powered by our open source Whisper V2 model) is currently available. |  whisper-1
+| spring.ai.openai.audio.transcription.options.model  | ID of the model to use for transcription. Available models: `gpt-4o-transcribe` (speech-to-text powered by GPT-4o), `gpt-4o-mini-transcribe` (speech-to-text powered by GPT-4o mini), or `whisper-1` (general-purpose speech recognition model, default). |  whisper-1
 | spring.ai.openai.audio.transcription.options.response-format | The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt. |  json
 | spring.ai.openai.audio.transcription.options.prompt | An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language. |
 | spring.ai.openai.audio.transcription.options.language | The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency. |