"SST" matching MCP servers:

Enables AI agents to send the same short audio clip to multiple speech-to-text providers and compare transcripts, CER/WER, latency, and estimated cost. It also lets agents check which providers are configured and estimate costs from a built-in price table.

Local Korean text-to-speech MCP server using a fine-tuned CosyVoice2 model, enabling voice synthesis directly from Claude or Codex with privacy and no API costs.