Voice Identify
Createdyangsenessa
Provides voice recognition and text extraction capabilities accessible via stdio and MCP.
About
Voice Identify offers voice recognition and text extraction services through both standard input/output (stdio) and the MCP (Message Communication Protocol). It supports voice recognition from files and base64 encoded data, providing structured voice recognition results that include language, emotion, audio type, speaker identification, and the recognized text. The service features separate entry points for stdio and MCP modes and includes build scripts for creating executable versions.
Key Features
- Voice recognition from file
- Supports stdio and MCP modes
- Voice recognition from base64 encoded data
- Structured voice recognition results
- Text extraction
- 0 GitHub stars
Use Cases
- Integrating voice recognition into applications via stdio
- Using MCP for remote voice recognition processing
- Analyzing audio data to extract text and related information
