openapi: 3.1.0 info: title: CometAPI Unified Audio API description: CometAPI is an OpenAI-compatible aggregator that exposes a single REST surface for 500+ AI models from multiple vendors (OpenAI, Anthropic, Google, xAI, DeepSeek, Alibaba, and more). Endpoints follow OpenAI's request/response shapes for chat, embeddings, images, video, and speech, so existing OpenAI SDK clients can switch by changing only the base URL and API key. version: 1.0.0 contact: name: CometAPI url: https://www.cometapi.com/ servers: - url: https://api.cometapi.com/v1 description: Production security: - bearerAuth: [] tags: - name: Audio description: Speech synthesis, transcription, and translation. paths: /audio/speech: post: operationId: createSpeech summary: Create speech description: Synthesize speech audio from text (TTS). tags: - Audio requestBody: required: true content: application/json: schema: type: object required: - model - input properties: model: type: string input: type: string voice: type: string response_format: type: string responses: '200': description: Audio bytes. /audio/transcriptions: post: operationId: createTranscription summary: Transcribe audio description: Transcribe an audio file to text using Whisper-class models. tags: - Audio requestBody: required: true content: multipart/form-data: schema: type: object properties: file: type: string format: binary model: type: string language: type: string responses: '200': description: Transcript. components: securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT externalDocs: description: CometAPI Documentation url: https://apidoc.cometapi.com/