Speak
Text to natural speech as MP3: 38 voices, 7 languages, 1,000 chars per call. Paid per call, x402.
Open the source (opens speak.kaneky.dev) https://speak.kaneky.dev
Before you use it
- Runs on someone else's server: what you send it leaves your machine.
What it is
MCP servers from dev.kaneky.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
Remote endpoint (streamable-http)
https://speak.kaneky.dev/mcp
From the server's entry in the official MCP Registry
Related
-
FunASR
MCP serversOpen-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
git clone https://github.com/modelscope/FunASR.git -
Speakeroo speaking coach
MCP serversAI speaking coach: feedback on speeches from text or audio, plus topics, pronunciation and rubrics.
-
Joe Speaking
MCP serversReview IELTS and CELPIP speaking practice, progress and feedback saved in Joe Speaking.
-
Before You Speak
MCP serversCreate English speaking practice scenes and read review progress in Before You Speak (开口前).
-
speakmanai
MCP serversMulti-agent AI pipeline that generates professional Solution Architecture Documents.
-
smart-speaker-mcp
MCP serversControl Google Home and Amazon Alexa speakers from Claude Desktop using natural language.
https://github.com/WeCodeBase/smart-speaker-mcp/releases/download/v1.0.0/smart-speaker-mcp-darwin-arm64@1.0.1