OpenAI
Official OpenAI REST operations for text-to-speech, transcription, and translation.
Connect this API to an AI agent Browse all specs
What you can do with OpenAI via MCP
Every endpoint below becomes a governed tool your AI agent (Claude, ChatGPT, or a customer-facing VX agent) can call — with scoped permissions, sandbox testing, and audit logs.
| Method | Path | Operation | Description |
|---|---|---|---|
| POST | /audio/speech |
createSpeech | Create speech Method: POST Path: /audio/speech IMPORTANT: This function has 3 REQUIRED parameter(s) and 2 OPTIONAL parameter(s) REQUIRED parameters MUST be provided OPTIONAL parameters can be omitted if not needed Parameters: Request Body: REQUIRED: - model: model parameter from application/json - input: input parameter from application/json - voice: voice parameter from application/json OPTIONAL: - response_format: response_format parameter from application/json - speed: speed parameter from application/json |
| POST | /audio/transcriptions |
createTranscription | Create transcription Method: POST Path: /audio/transcriptions IMPORTANT: This function has 2 REQUIRED parameter(s) and 2 OPTIONAL parameter(s) REQUIRED parameters MUST be provided OPTIONAL parameters can be omitted if not needed Parameters: Form Data: REQUIRED: - file: file parameter from multipart/form-data - model: model parameter from multipart/form-data OPTIONAL: - language: language parameter from multipart/form-data - response_format: response_format parameter from multipart/form-data |
| POST | /audio/translations |
createTranslation | Create translation Method: POST Path: /audio/translations IMPORTANT: This function has 2 REQUIRED parameter(s) and 1 OPTIONAL parameter(s) REQUIRED parameters MUST be provided OPTIONAL parameters can be omitted if not needed Parameters: Form Data: REQUIRED: - file: file parameter from multipart/form-data - model: model parameter from multipart/form-data OPTIONAL: - response_format: response_format parameter from multipart/form-data |
Usage guide
## Authentication Create an OpenAI API key in the API dashboard and send it as `Authorization: Bearer $OPENAI_API_KEY`. Keep the key server-side. ## Text to speech Call `POST /audio/speech` with JSON containing `model`, `input`, and `voice`. The response is an audio stream. ## Speech to text Call `POST /audio/transcriptions` or `/audio/translations` as multipart form data with `file` and `model`. Official docs: https://developers.openai.com/api/reference/resources/audio
How to use this spec
- Create a free VX Agents account (sandbox tools included).
- Open the marketplace and connect “OpenAI” to an agent.
- Expose it as an MCP server for Claude/ChatGPT, or chat with it directly.