Server facts
speech-ai-examples MCP Server
Project
- Author
- fasuizu-br
- Repository
- github.com/fasuizu-br/speech-ai-examples
- Website
- brainiall.com
- License
- MIT
- Category
- Design & Creative
Tech
- Runtime / language
- python
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 3
- Last commit
- Data as of
Tags
- Text To Speech
- ai
- audio
- language learning
- mcp
- pronunciation
- speech assessment
- speech to text
Overview
English pronunciation practice anchors this collection of Brainiall speech integrations. Developers can submit recorded audio alongside an expected passage to receive scores for the recording, sentences, individual words, and phonemes. Assessment results include IPA and ARPAbet representations, the recognized transcript, confidence, warnings, and audio-quality measurements. A separate phoneme inventory supplies symbols, example words, and sound categories. The repository also includes an interactive pronunciation tutor, connecting these assessment features to a concrete learning workflow.
Transcription and speech generation extend the agent-facing toolset beyond assessment. English transcription provides word timing and confidence, while the Whisper option handles multilingual recordings with automatic language detection and optional speaker labels. Speech synthesis turns English text into base64-encoded WAV audio, with selectable American or British voices and adjustable speed; a voice-listing tool exposes the available choices. Health checks report service status and whether the relevant models are loaded. Python, JavaScript, and curl examples accompany MCP configuration files for Claude Desktop and Cursor, giving developers both API usage examples and agent connection settings.
speech-ai-examples setup notes
- speech-ai-examples records stdio only; confirm a network transport upstream before planning remote access.