Speech AI - Pronunciation, STT & TTS
内容与创意by fasuizu-br
为 AI agents 提供发音评分、STT 与 TTS 能力,支持语音识别、朗读与交互。
什么是 Speech AI - Pronunciation, STT & TTS?
为 AI agents 提供发音评分、STT 与 TTS 能力,支持语音识别、朗读与交互。
README
Speech AI Plugin
Speech processing suite for AI coding assistants. Pronunciation assessment, speech-to-text, and text-to-speech — all via MCP.
What It Does
- Pronunciation Assessment: Score English pronunciation at phoneme, word, and sentence levels (0-100). Exceeds human inter-annotator agreement.
- Speech-to-Text: Transcribe English audio with word-level timestamps and confidence scores. Sub-300ms latency.
- Text-to-Speech: Generate natural speech with 12 English voices (American and British). Speed control 0.5x-2.0x.
Installation
Claude Code
/plugin install speech-ai
Cursor
/add-plugin speech-ai
Manual (any MCP client)
Add to your MCP settings:
{
"mcpServers": {
"speech-ai": {
"url": "https://pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io/mcp",
"headers": {
"Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
}
}
}
Get an API Key
Visit brainiall.com or subscribe via Azure Marketplace.
Skills
| Skill | Description |
|---|---|
assess-pronunciation | Evaluate pronunciation quality from audio |
transcribe-audio | Convert audio to text with timestamps |
speech-workflow | Full practice loop: listen, record, score, improve |
Agent
- pronunciation-tutor: Interactive pronunciation coaching agent with structured practice sessions
Support
- Email: fasuizu@brainiall.com
- Website: https://brainiall.com
License
Plugin configuration files: MIT. The Speech AI API is a proprietary commercial service.
常见问题
Speech AI - Pronunciation, STT & TTS 是什么?
为 AI agents 提供发音评分、STT 与 TTS 能力,支持语音识别、朗读与交互。
相关 Skills
平面设计
by anthropics
先生成视觉哲学,再落地成原创海报、艺术画面或其他静态设计,输出 .png/.pdf,强调构图、色彩与空间表达,适合需要高完成度视觉成品的场景。
✎ 做海报、插画或静态视觉稿时,用它能快速产出兼顾美感与版式的PNG/PDF成品,原创设计更省心,也更适合规避版权风险。
文档共著
by anthropics
围绕文档、提案、技术规格、决策记录等写作任务,按上下文收集、结构迭代、读者测试三步协作共创,减少信息遗漏,写出更清晰、经得起他人阅读的内容。
✎ 写文档、方案或技术规格时容易思路散、信息漏,它用结构化共著流程帮你高效传递上下文、反复打磨内容,还能从读者视角做验证。
内部沟通
by anthropics
按公司常用模板和语气快速起草内部沟通内容,覆盖 3P 更新、状态报告、领导汇报、项目进展、事故复盘、FAQ 与 newsletter,适合需要统一格式的团队沟通场景。
✎ 按公司偏好的模板快速产出状态汇报、领导更新和 FAQ,既省去反复改稿,也让内部沟通更统一、更专业。
相关 MCP Server
by nirholas
免费的加密新闻聚合 MCP,汇集 Bitcoin、Ethereum、DeFi、Solana 与 altcoins 资讯源。
by alisaitteke
用于Adobe Photoshop自动化的MCP server,让AI assistants直接控制Photoshop。
by roomi-fields
Automate Google NotebookLM — Q&A with citations, audio, video, content generation