Gladia
Createdgladiaio
Enables interaction with Speech-to-Text and Audio Intelligence APIs for transcription, analysis, and translation.
About
Gladia is an official Model Context Protocol (MCP) server that facilitates interaction with Speech-to-Text and Audio Intelligence APIs. It allows MCP clients like Claude Desktop, Cursor, Windsurf, and OpenAI Agents to transcribe audio, analyze speech, translate content, and perform other audio-related tasks. With its easy-to-use CLI and asynchronous API, Gladia seamlessly integrates advanced audio processing capabilities into various applications and workflows.
Key Features
- Configurable logging and CORS support
- Audio transcription with speaker diarization
- Async API with FastAPI
- Real-time speech-to-text
- 0 GitHub stars
- Audio intelligence capabilities (translation, summarization, NER, sentiment analysis, content moderation, chapterization)
Use Cases
- Transcribing audio files and identifying different speakers
- Converting recordings to text and translating them to other languages
- Analyzing sentiment and emotions in speech
