warehack.ing/mcspeak
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
23 Commits 1 Branch 0 Tags
Commit Graph

3 Commits

Author SHA1 Message Date
Ryan Malloy
d054caa43c Rename project to mcspeak, add README 
Rename all user-facing references from tts-mcp to mcspeak: service name,
container, compose project, Dockerfile CMD, FastMCP instance, MCP config,
startup logs, temp dir, and CLAUDE.md header. Python module stays tts_mcp
(import name != package name is standard practice).

README covers quick start, MCP tools, engines, features, config, Docker
setup, and architecture.
 2026-03-04 19:46:25 -07:00
Ryan Malloy
538b8a513e Replace Ollama with llama-server for 15x Orpheus throughput 
Build llama.cpp from source with SM 120 CUDA kernels and FORCE_CUBLAS
for RTX 5070 Blackwell. Rewrite OrpheusEngine to stream tokens via SSE
and decode SNAC in overlapping 28-token batches (4 frames), replacing
the blocking requests+stream:false approach.

Performance: 13.5 → 170-213 tok/s. 100s audio generates in ~48s (2x
faster than realtime). Replaces requests with httpx async client.

Also switch MCP transport to stateless_http mode so container restarts
don't invalidate client sessions.
 2026-02-21 21:33:23 -07:00
Ryan Malloy
2fd84f0df7 Initial TTS MCP server with 3 engines 
FastMCP 3.0 Streamable HTTP server exposing Piper (Wyoming/Docker),
Kokoro (ONNX), and Orpheus (Ollama+SNAC) as MCP tools. Includes a
FIFO speech queue so concurrent agents don't talk over each other —
waiting callers get queue position updates via ctx.info().

Tools: speak, generate_audio, list_voices, list_engines
Resource: audio://recent
 2026-02-20 18:10:15 -07:00