Files
zclaw_openfang/hands/speech.HAND.toml
iven a71c4138cc
Some checks failed
CI / Lint & TypeCheck (push) Has been cancelled
CI / Unit Tests (push) Has been cancelled
CI / Build Frontend (push) Has been cancelled
CI / Rust Check (push) Has been cancelled
CI / Security Scan (push) Has been cancelled
CI / E2E Tests (push) Has been cancelled
fix(audit): 修复深度审计发现的 P0/P1 问题 (8项)
基于 DEEP_AUDIT_REPORT.md 修复 2 CRITICAL + 4 HIGH + 1 MEDIUM 问题:

- C1: PromptOnly 技能集成 LLM 调用 — 定义 LlmCompleter trait,
  通过 LlmDriverAdapter 桥接 zclaw_runtime::LlmDriver,
  PromptOnlySkill.execute() 现在调用 LLM 生成内容
- C2: 反思引擎空记忆 bug — 新增 query_memories_for_reflection()
  从 VikingStorage 查询真实记忆传入 reflect()
- H7: Agent Store 接口适配 — KernelClient 添加 listClones/createClone/
  deleteClone/updateClone 方法,映射到 agent_* 命令
- H8: Hand 审批检查 — hand_execute 执行前检查 needs_approval,
  需审批返回 pending_approval 状态
- M1: 幽灵命令注册 — 注册 hand_get/hand_run_status/hand_run_list
  三个 Tauri 桩命令
- H1/H2: SpeechHand/TwitterHand 添加 demo 标签
- H5: 归档过时 VERIFICATION_REPORT

文档更新: DEEP_AUDIT_REPORT.md 标记修复状态,README.md 更新
关键指标和变更历史。整体完成度从 ~50% 提升至 ~58%。
2026-03-27 09:36:50 +08:00

128 lines
2.6 KiB
TOML

# Speech Hand - 语音合成能力包
#
# ZCLAW Hand 配置
# 提供文本转语音 (TTS) 能力,支持多种语音和语言
[hand]
name = "speech"
version = "1.0.0"
description = "语音合成能力包 - 将文本转换为自然语音输出"
author = "ZCLAW Team"
type = "media"
requires_approval = false
timeout = 120
max_concurrent = 3
tags = ["speech", "tts", "voice", "audio", "education", "accessibility", "demo"]
[hand.config]
# TTS 提供商: browser, azure, openai, elevenlabs, local
provider = "browser"
# 默认语音
default_voice = "default"
# 默认语速 (0.5 - 2.0)
default_rate = 1.0
# 默认音调 (0.5 - 2.0)
default_pitch = 1.0
# 默认音量 (0 - 1.0)
default_volume = 1.0
# 语言代码
default_language = "zh-CN"
# 是否缓存音频
cache_audio = true
# Azure TTS 配置 (如果 provider = "azure")
[hand.config.azure]
# voice_name = "zh-CN-XiaoxiaoNeural"
# region = "eastasia"
# OpenAI TTS 配置 (如果 provider = "openai")
[hand.config.openai]
# model = "tts-1"
# voice = "alloy"
# 浏览器 TTS 配置 (如果 provider = "browser")
[hand.config.browser]
# 使用系统默认语音
use_system_voice = true
# 语音名称映射
voice_mapping = { "zh-CN" = "Microsoft Huihui", "en-US" = "Microsoft David" }
[hand.triggers]
manual = true
schedule = false
webhook = false
[[hand.triggers.events]]
type = "chat.intent"
pattern = "朗读|念|说|播放语音|speak|read|say|tts"
priority = 5
[hand.permissions]
requires = [
"speech.synthesize",
"speech.play",
"speech.stop"
]
roles = ["operator.read"]
[hand.rate_limit]
max_requests = 100
window_seconds = 3600
[hand.audit]
log_inputs = true
log_outputs = false # 音频不记录
retention_days = 3
# 语音动作定义
[[hand.actions]]
id = "speak"
name = "朗读文本"
description = "将文本转换为语音并播放"
params = { text = "string", voice = "string?", rate = "number?", pitch = "number?" }
[[hand.actions]]
id = "speak_ssml"
name = "朗读 SSML"
description = "使用 SSML 标记朗读文本(支持更精细控制)"
params = { ssml = "string", voice = "string?" }
[[hand.actions]]
id = "pause"
name = "暂停播放"
description = "暂停当前语音播放"
params = {}
[[hand.actions]]
id = "resume"
name = "继续播放"
description = "继续暂停的语音播放"
params = {}
[[hand.actions]]
id = "stop"
name = "停止播放"
description = "停止当前语音播放"
params = {}
[[hand.actions]]
id = "list_voices"
name = "列出可用语音"
description = "获取可用的语音列表"
params = { language = "string?" }
[[hand.actions]]
id = "set_voice"
name = "设置默认语音"
description = "更改默认语音设置"
params = { voice = "string", language = "string?" }