anvil-serving-voice-ops
Operate topology-owned anvil-serving voice audio and Realtime proxy lifecycle, Mini-to-Dark loopback forwarding, profiles, sidecars, and bounded voice benchmarks. Use for voice status, logs, start/stop/restart, OpenClaw Talk topology checks, and voice evidence that must remain separate from LLM serve qualification evidence.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- anvil-serving-voice-ops
- description
- Operate topology-owned anvil-serving voice audio and Realtime proxy lifecycle, Mini-to-Dark loopback forwarding, profiles, sidecars, and bounded voice benchmarks. Use for voice status, logs, start/stop/restart, OpenClaw Talk topology checks, and voice evidence that must remain separate from LLM serve qualification evidence.
03 SKILL.md 正文
Anvil Serving Voice Ops
Use this skill for voice-pipeline operations: validating sidecar manifests, rendering speech-to-speech commands, managing topology-owned STT/TTS, managing the persistent Mini Realtime proxy, selecting profiles, running the Mini-local forwarding bridge, and collecting bounded voice benchmarks.
Start Here
- Read
README.md,CLAUDE.md, anddocs/OPERATOR-SKILLS-AND-SUBAGENTS.mdbefore changing behavior or reporting voice results as product evidence. - Prefer
voice_managefor structured STT/TTS lifecycle andvoice_proxy_managefor persistent Realtime proxy lifecycle. Use the existing CLI verbs for foreground, profile, sidecar, bridge, and benchmark operations that do not have MCP wrappers:anvil-serving voice sidecar validate,anvil-serving voice sidecar command,anvil-serving voice sidecar compose,anvil-serving voice audio {up|down|status|logs},anvil-serving voice profiles {list|validate},anvil-serving voice proxy {run|up|down|restart|status|logs|bridge}, andanvil-serving voice benchmark. - Use
127.0.0.1for local URLs. Do not introducelocalhost. - Pass secrets by environment variable name only. Do not put literal API keys in manifests, commands, compose snippets, packets, or logs.
- Record the command host before interpreting loopback. In the reference
OpenClaw topology, Companion Node runs Gateway plus Anvil Voice Realtime/proxy
and reserves its 16 GB RAM for OpenClaw, Claude Code, and Codex. Do not run
STT/TTS/LLM model serves on Mini for reference testing. Use
dark-audiofor Dark bridge ports ormini-dark-audio-proxyfor Mini proxy ports forwarding to Dark.mini-audiois an explicit optional same-host/local-audio mode only. A non-gateway checkout cannot validate Mini-local proxy paths by calling its own127.0.0.1. - Treat voice benchmark output as voice-pipeline evidence. Voice results do not qualify an LLM serve or change a capability alias.
- Route multi-sample STT corpus qualification to
skills/anvil-serving-stt-benchmark/SKILL.md. Keep this skill for single-turn audio/voice-pipeline evidence and topology lifecycle. - Do not introduce one-off lifecycle, proxy, or port-forwarding scripts as the
operational path. If repeatable voice operation needs a new control, it
belongs in
anvil-serving voiceand, when agent-operated, MCP/controller.
Gates
Stop for a human gate before public or non-loopback Realtime binds, exposing a Realtime token, changing cloud/STT/TTS spend, installing or updating external speech-to-speech packages, or starting long-running foreground services on a shared host.
voice sidecar command --with-auth and voice sidecar compose --with-auth
render environment variable references for authenticated router calls. The
command path returns argv, so explicitly warn that the env-var reference appears
in process argv. The compose path includes an auth exposure comment in the
rendered service. Use either path only on private hosts where process and
Docker metadata are protected.
Never use anvil-serving voice benchmark as a shortcut for LLM serve
qualification. Voice benchmarks measure the voice pipeline: turn latency,
TTFA, audio/STT/TTS behavior, realtime transport, and user-perceived loop
quality. They can support a voice-pipeline status report, but an LLM serve
still requires its own preflight, benchmark evidence, independent review, and
human approval before an operator changes a capability alias.
Use workflow_packet_validate before handing a voice packet to the broader
workbench. Voice artifacts must remain explicitly marked as non-promotion
evidence.
Playbooks
- Sidecar manifest validation:
anvil-serving voice sidecar validate --config <manifest>. - Host command rendering:
anvil-serving voice sidecar command --config <manifest> --json; add--with-authonly when the operator accepts the argv exposure warning. - Compose rendering:
anvil-serving voice sidecar compose --config <manifest>; inspect loopback ports,host.docker.internalrouting, image name, and auth comments. - Managed audio serves:
prefer
voice_managefor agent/controller operation. The CLI equivalents areanvil-serving voice audio up --topology <topology> --config <manifest>andvoice audio down; preview mutations first and require--confirmfor live execution. Useanvil-serving voice audio statusand boundedanvil-serving voice audio logsfor reads. External lifecycle serves should be reported as skipped rather than forced into local Docker control. - Profile selection:
anvil-serving voice profiles list --config <manifest>to list profiles,anvil-serving voice profiles validate --config <manifest> --profile <name>before live work, then add--profile <name>to audio, proxy, orvoice benchmarkwhen switching audio topology. For reference OpenClaw Talk and candidate benchmarks, keep Mini model-free and select Dark-host audio or a Mini-side proxy to Dark. Usemini-audioonly when explicitly testing the optional same-host/local-audio mode. - Mini-to-Dark audio bridge:
anvil-serving voice proxy bridge --topology <topology> --config <manifest> --profile mini-dark-audio-proxy --dry-runfirst. Run it on Mini. Require topology-derived Dark targets and reject every non-loopback Mini listener. - Realtime proxy:
prefer
voice_proxy_managefor the persistent Mini process. The CLI equivalents areanvil-serving voice proxy upfor persistent operation andanvil-serving voice proxy runfor a foreground diagnostic. Usedown/restartonly after preview and explicit confirmation; use boundedstatus/logsfor inspection. Treat unreachable STT/TTS/router endpoints as blockers. Never start audio lifecycle implicitly. - Bounded benchmark:
anvil-serving voice benchmark --config <manifest>and capture JSON asvoice-pipelineevidence withpromoted=false. The benchmark is an endpoint client, not a Realtime-proxy lifecycle operation, so it has no proxy owner. Use--scope audiofor an LLM-free TTS-to-STT loop. Keep audio topology and LLM selection separate:--profileselects the audio path and--candidate-overlay <toml>selects a candidate LLM configuration. Do not combine--candidate-overlaywith direct candidate flags. A voice benchmark does not replaceanvil-serving eval preflight, capacity benchmarking, or repeatedanvil-serving eval benchmark qualityevidence for LLM serve qualification. Publish a meaningful retained result throughskills/anvil-serving-benchmark-docs/SKILL.md; keep measured hardware separate from protected/co-resident hardware and retainpromoted=false. Apply itsreferences/artifact-set-contract.mdandanvil-serving.benchmark-artifact-set/v1template around the nativevoice-benchmark-evidence/v1file so workload, plan, identity, raw evidence, friction, restoration, and decision roles remain explicit. Use that contract's publication-ready result card and publication summary when the retained voice artifact is meaningful; a format-only refresh does not rerun the bounded voice benchmark. - Multi-sample STT qualification:
use
anvil-serving voice corpus prepare|validateandanvil-serving voice benchmark --scope sttthrough the canonicalanvil-serving-stt-benchmarkskill. Do not collapse its primary human set, separate synthetic set, repeated schedule, concurrency lane, or restoration checks into the bounded one-turn benchmark above.
Result Packet
Return an operator-workflow/v1 packet when coordinating with the broader
workbench. Use artifacts entries with kind: "voice-benchmark" or
kind: "voice-sidecar-render", evidence_scope: "voice-pipeline", and
promotion_quality_evidence: false. Keep advisory_priors empty unless
external voice-specific priors are explicitly identified as advisory-only. Keep
promoted=false and human_gate_required=true for any workflow that asks for
a capability-alias change, public binds, cloud enablement, or long-running service
starts.
If the existing voice and voice sidecar verbs cannot cover the request,
report the missing wrapper as a product gap after showing the closest safe
existing command and why it is insufficient.
04 同仓库更多 Skills
voice
暂无简介
workbench
暂无简介
workbench
暂无简介
workbench
暂无简介
anvil-serving-stt-benchmark
Prepare, validate, execute, compare, and publish reproducible multi-sample speech-to-text qualifications in anvil-serving. Use for STT model bakeoffs, corpus-based WER/CER and latency testing, candidate overlays, concurrency tests, restoration checks, and fail-closed stt-benchmark-evidence/v1 artifacts. Do not use for a single voice-pipeline turn or LLM qualification.
anvil-serving-release-readiness
Gate an Anvil Serving package release and coordinated live deployment across Windows, Primary Node, Companion Node, the controller, router, Hermes, Pi, and OpenClaw. Use when a change will be merged, tagged, published, or deployed and exact manifest dependencies, version parity, recovery policy, and outage-free client smokes must be proven.