feat: lazy daemon mode with voxtream-server streaming#36
Merged
pszymkowiak merged 1 commit intomainfrom Mar 18, 2026
Merged
Conversation
- Add `vox daemon start/stop/status` — local HTTP server keeps models warm - Daemon manages voxtream-server as child process (WebSocket proxy) - Transparent routing: heavy backends auto-route through daemon if running - Idle auto-shutdown (default 5min, configurable) - Update README with real benchmark data (streaming: 170ms first-frame CUDA) - Add .cargo/config.toml with Metal aliases for macOS dev builds - Add tokio rt-multi-thread, macros, signal, time features Benchmark results (voxtream streaming, model warm): M2 Pro CPU: 3.3s first audio RTX 4070 Ti SUPER: 170ms first audio (paper: 74ms) Closes #30
Contributor
Author
📊 Automated PR Analysis
SummaryAdds a lazy daemon mode ( Review Checklist
Linked issues: #30 🤖 Analyzed automatically by wshm · This is an automated analysis, not a human review. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
vox daemon start/stop/status— keeps heavy TTS models warm in memoryvox -b voxtream "text"auto-routes through daemon if runningBenchmark (streaming, model warm)
Closes #30
Test plan
cargo build --features metalpassesvox daemon start→vox daemon status→vox daemon stoplifecycle