saybench MCP Server
renan-martini/saybench
Benchmark the full voice-AI pipeline on your own audio — STT (batch + streaming), LLM TTFT, speech-to-speech, and TTS. WER by failure mode, keyterm recall, real-time-paced latency, cost columns, a CI regression gate, and an MCP server for coding agents.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
renan-martini/saybench is a Go MCP server licensed under MIT. Benchmark the full voice-AI pipeline on your own audio — STT (batch + streaming), LLM TTFT, speech-to-speech, and TTS. WER by failure mode, keyterm recall, real-time-paced latency, cost columns, a CI regression gate, and an MCP server for coding agents.
Ranked #4080 out of 24850 indexed tools.
Ecosystem
Score Breakdown
1 stars → early stage
Last commit 15d ago → recently updated
No issues filed → no history to score
0 contributors → solo project
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
How to Improve
Matched Queries
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.