openapi: 3.2.0 info: title: SiliconFlow Cloud Platform Audio API description: SiliconFlow provides an AI inference cloud with OpenAI- and Anthropic-compatible REST APIs covering chat completions, messages, completions, embeddings, reranking, image generation, video generation, audio (speech, transcription, voice catalogue), models, and user account metadata. All endpoints authenticate with a Bearer API key in the Authorization header. version: v1 contact: name: SiliconFlow url: https://docs.siliconflow.com/ servers: - url: https://api.siliconflow.com/v1 description: SiliconFlow inference API security: - BearerAuth: [] tags: - name: Audio paths: /audio/transcriptions: post: summary: Create Audio Transcription description: Creates an audio transcription from an input audio file. operationId: createTranscription tags: - Audio responses: '200': description: OK /audio/speech: post: summary: Create Audio Speech description: Generate audio from input text. operationId: createSpeech tags: - Audio responses: '200': description: OK /audio/voices: get: summary: List User Voices description: Get list of user-defined voice styles. operationId: listVoices tags: - Audio responses: '200': description: OK post: summary: Upload User Voice description: Upload a user-provided voice style. operationId: createVoice tags: - Audio responses: '200': description: OK /audio/voices/{id}: parameters: - name: id in: path required: true schema: type: string delete: summary: Delete User Voice description: Delete a user-defined voice style. operationId: deleteVoice tags: - Audio responses: '204': description: No Content components: securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: API Key description: 'Bearer API key, format `Authorization: Bearer `.'