OpenAI Speech-to-Text transcriptions MCP Server logo

OpenAI Speech-to-Text transcriptions MCP Server

by Ichigo3766

This MCP server provides audio transcription capabilities using OpenAI's API. It allows users to transcribe audio files using the `transcribe_audio` tool.

View on GitHub

Last updated: N/A

What is OpenAI Speech-to-Text transcriptions MCP Server?

This is an MCP server that leverages the OpenAI API to transcribe audio files. It exposes a tool that can be integrated into other applications or workflows.

How to use OpenAI Speech-to-Text transcriptions MCP Server?

  1. Clone the repository. 2. Install dependencies using npm install. 3. Build the server using npm run build. 4. Set your OpenAI API key as an environment variable. 5. Configure the server in your MCP environment as shown in the README, replacing the placeholder path with the actual path to your cloned repository.

Key features of OpenAI Speech-to-Text transcriptions MCP Server

  • Transcribes audio files using OpenAI's API

  • Offers a transcribe_audio tool with filepath as a required parameter

  • Supports optional parameters like save_to_file and language

  • Configurable OpenAI API key, base URL, and model

Use cases of OpenAI Speech-to-Text transcriptions MCP Server

  • Automated transcription of meeting recordings

  • Generating subtitles for video content

  • Converting voice memos to text

  • Integrating speech-to-text into voice-activated applications

FAQ from OpenAI Speech-to-Text transcriptions MCP Server

What API key do I need?

You need an OpenAI API key with access to the Speech-to-Text API.

Can I specify the language of the audio?

Yes, you can use the language parameter with an ISO-639-1 language code.

How do I save the transcription to a file?

Set the save_to_file parameter to true when calling the transcribe_audio tool.

What audio file formats are supported?

The supported audio file formats depend on the OpenAI API. Refer to the OpenAI documentation for details.

Can I use a custom OpenAI model?

Yes, you can specify the OpenAI model to use by setting the OPENAI_MODEL environment variable.