Add sound generation support

src/AiClient.php

@@ -362,6 +362,30 @@ public static function generateSpeechResult(
         return self::getConfiguredPromptBuilder($prompt, $modelOrConfig, $registry)->generateSpeechResult();
     }
 
+    /**
+     * Generates sound using the traditional API approach.
+     *
+     * @since 1.4.0
+     *
+     * @param Prompt $prompt The prompt content.
+     * @param ModelInterface|ModelConfig|null $modelOrConfig Optional specific model to use,
+     *                                                        or model configuration for auto-discovery,
+     *                                                        or null for defaults.
+     * @param ProviderRegistry|null $registry Optional custom registry. If null, uses default.
+     * @return GenerativeAiResult The generation result.
+     *
+     * @throws \InvalidArgumentException If the prompt format is invalid.
+     * @throws \RuntimeException If no suitable model is found.
+     */
+    public static function generateSoundResult(
+        $prompt,
+        $modelOrConfig = null,
+        ?ProviderRegistry $registry = null
+    ): GenerativeAiResult {
+        self::validateModelOrConfigParameter($modelOrConfig);
+        return self::getConfiguredPromptBuilder($prompt, $modelOrConfig, $registry)->generateSoundResult();
+    }
+
     /**
      * Generates a video using the traditional API approach.
      *

src/Builders/PromptBuilder.php

@@ -25,6 +25,7 @@
 use WordPress\AiClient\Providers\Models\DTO\ModelRequirements;
 use WordPress\AiClient\Providers\Models\Enums\CapabilityEnum;
 use WordPress\AiClient\Providers\Models\ImageGeneration\Contracts\ImageGenerationModelInterface;
+use WordPress\AiClient\Providers\Models\SoundGeneration\Contracts\SoundGenerationModelInterface;
 use WordPress\AiClient\Providers\Models\SpeechGeneration\Contracts\SpeechGenerationModelInterface;
 use WordPress\AiClient\Providers\Models\TextGeneration\Contracts\TextGenerationModelInterface;
 use WordPress\AiClient\Providers\Models\TextToSpeechConversion\Contracts\TextToSpeechConversionModelInterface;
@@ -758,6 +759,9 @@ private function inferCapabilityFromModelInterfaces(ModelInterface $model): ?Cap
         if ($model instanceof SpeechGenerationModelInterface) {
             return CapabilityEnum::speechGeneration();
         }
+        if ($model instanceof SoundGenerationModelInterface) {
+            return CapabilityEnum::soundGeneration();
+        }
         if ($model instanceof VideoGenerationModelInterface) {
             return CapabilityEnum::videoGeneration();
         }
@@ -871,6 +875,18 @@ public function isSupportedForSpeechGeneration(): bool
         return $this->isSupported(CapabilityEnum::speechGeneration());
     }
 
+    /**
+     * Checks if the prompt is supported for sound generation.
+     *
+     * @since 1.4.0
+     *
+     * @return bool True if sound generation is supported.
+     */
+    public function isSupportedForSoundGeneration(): bool
+    {
+        return $this->isSupported(CapabilityEnum::soundGeneration());
+    }
+
     /**
      * Checks if the prompt is supported for music generation.
      *
@@ -1012,6 +1028,18 @@ private function executeModelGeneration(
             return $model->generateSpeechResult($messages);
         }
 
+        if ($capability->isSoundGeneration()) {
+            if (!$model instanceof SoundGenerationModelInterface) {
+                throw new RuntimeException(
+                    sprintf(
+                        'Model "%s" does not support sound generation.',
+                        $model->metadata()->getId()
+                    )
+                );
+            }
+            return $model->generateSoundResult($messages);
+        }
+
         if ($capability->isVideoGeneration()) {
             if (!$model instanceof VideoGenerationModelInterface) {
                 throw new RuntimeException(
@@ -1102,6 +1130,24 @@ public function convertTextToSpeechResult(): GenerativeAiResult
         return $this->generateResult(CapabilityEnum::textToSpeechConversion());
     }
 
+    /**
+     * Generates a sound result from the prompt.
+     *
+     * @since 1.4.0
+     *
+     * @return GenerativeAiResult The generated result containing sound audio candidates.
+     * @throws InvalidArgumentException If the prompt or model validation fails.
+     * @throws RuntimeException If the model doesn't support sound generation.
+     */
+    public function generateSoundResult(): GenerativeAiResult
+    {
+        // Include audio in output modalities
+        $this->includeOutputModalities(ModalityEnum::audio());
+
+        // Generate and return the result with sound generation capability
+        return $this->generateResult(CapabilityEnum::soundGeneration());
+    }
+
     /**
      * Generates a video result from the prompt.
      *
@@ -1251,6 +1297,39 @@ public function generateSpeeches(?int $candidateCount = null): array
         return $this->generateSpeechResult()->toFiles();
     }
 
+    /**
+     * Generates sound from the prompt.
+     *
+     * @since 1.4.0
+     *
+     * @return File The generated sound audio file.
+     * @throws InvalidArgumentException If the prompt or model validation fails.
+     * @throws RuntimeException If no audio is generated.
+     */
+    public function generateSound(): File
+    {
+        return $this->generateSoundResult()->toFile();
+    }
+
+    /**
+     * Generates multiple sound outputs from the prompt.
+     *
+     * @since 1.4.0
+     *
+     * @param int|null $candidateCount The number of sound outputs to generate.
+     * @return list<File> The generated sound audio files.
+     * @throws InvalidArgumentException If the prompt or model validation fails.
+     * @throws RuntimeException If no audio is generated.
+     */
+    public function generateSounds(?int $candidateCount = null): array
+    {
+        if ($candidateCount !== null) {
+            $this->usingCandidateCount($candidateCount);
+        }
+
+        return $this->generateSoundResult()->toFiles();
+    }
+
     /**
      * Generates a video from the prompt.
      *

src/Providers/Models/Enums/CapabilityEnum.php

@@ -16,6 +16,7 @@
  * @method static self textToSpeechConversion() Creates an instance for TEXT_TO_SPEECH_CONVERSION capability.
  * @method static self speechGeneration() Creates an instance for SPEECH_GENERATION capability.
  * @method static self musicGeneration() Creates an instance for MUSIC_GENERATION capability.
+ * @method static self soundGeneration() Creates an instance for SOUND_GENERATION capability.
  * @method static self videoGeneration() Creates an instance for VIDEO_GENERATION capability.
  * @method static self embeddingGeneration() Creates an instance for EMBEDDING_GENERATION capability.
  * @method static self chatHistory() Creates an instance for CHAT_HISTORY capability.
@@ -24,6 +25,7 @@
  * @method bool isTextToSpeechConversion() Checks if the capability is TEXT_TO_SPEECH_CONVERSION.
  * @method bool isSpeechGeneration() Checks if the capability is SPEECH_GENERATION.
  * @method bool isMusicGeneration() Checks if the capability is MUSIC_GENERATION.
+ * @method bool isSoundGeneration() Checks if the capability is SOUND_GENERATION.
  * @method bool isVideoGeneration() Checks if the capability is VIDEO_GENERATION.
  * @method bool isEmbeddingGeneration() Checks if the capability is EMBEDDING_GENERATION.
  * @method bool isChatHistory() Checks if the capability is CHAT_HISTORY.
@@ -55,6 +57,11 @@ class CapabilityEnum extends AbstractEnum
      */
     public const MUSIC_GENERATION = 'music_generation';
 
+    /**
+     * Sound generation capability.
+     */
+    public const SOUND_GENERATION = 'sound_generation';
+
     /**
      * Video generation capability.
      */

src/Providers/Models/SoundGeneration/Contracts/SoundGenerationModelInterface.php

@@ -0,0 +1,28 @@
+<?php
+
+declare(strict_types=1);
+
+namespace WordPress\AiClient\Providers\Models\SoundGeneration\Contracts;
+
+use WordPress\AiClient\Messages\DTO\Message;
+use WordPress\AiClient\Results\DTO\GenerativeAiResult;
+
+/**
+ * Interface for models that support sound generation.
+ *
+ * Provides synchronous methods for generating sounds from prompts.
+ *
+ * @since 1.4.0
+ */
+interface SoundGenerationModelInterface
+{
+    /**
+     * Generates sound from a prompt.
+     *
+     * @since 1.4.0
+     *
+     * @param list<Message> $prompt Array of messages containing the sound generation prompt.
+     * @return GenerativeAiResult Result containing generated sound audio.
+     */
+    public function generateSoundResult(array $prompt): GenerativeAiResult;
+}

src/Providers/Models/SoundGeneration/Contracts/SoundGenerationOperationModelInterface.php

@@ -0,0 +1,28 @@
+<?php
+
+declare(strict_types=1);
+
+namespace WordPress\AiClient\Providers\Models\SoundGeneration\Contracts;
+
+use WordPress\AiClient\Messages\DTO\Message;
+use WordPress\AiClient\Operations\DTO\GenerativeAiOperation;
+
+/**
+ * Interface for models that support asynchronous sound generation operations.
+ *
+ * Provides methods for initiating long-running sound generation tasks.
+ *
+ * @since 1.4.0
+ */
+interface SoundGenerationOperationModelInterface
+{
+    /**
+     * Creates a sound generation operation.
+     *
+     * @since 1.4.0
+     *
+     * @param list<Message> $prompt Array of messages containing the sound generation prompt.
+     * @return GenerativeAiOperation The initiated sound generation operation.
+     */
+    public function generateSoundOperation(array $prompt): GenerativeAiOperation;
+}

tests/unit/AiClientTest.php

@@ -514,6 +514,7 @@ public function testTraditionalMethodsAcceptModelConfig(): void
             'generateImageResult',
             'convertTextToSpeechResult',
             'generateSpeechResult',
+            'generateSoundResult',
             'generateVideoResult'
         ];
 
@@ -573,6 +574,7 @@ public function aiClientMethodsProvider(): array
             'generateImageResult' => ['generateImageResult'],
             'convertTextToSpeechResult' => ['convertTextToSpeechResult'],
             'generateSpeechResult' => ['generateSpeechResult'],
+            'generateSoundResult' => ['generateSoundResult'],
             'generateVideoResult' => ['generateVideoResult'],
         ];
     }
@@ -705,6 +707,7 @@ public function testModelConfigPassedToAllMethods(): void
             'generateImageResult',
             'convertTextToSpeechResult',
             'generateSpeechResult',
+            'generateSoundResult',
             'generateVideoResult'
         ];