Audio PTBR

Audio PT Auto-Reply v2.0.1 - Premium Voice Interface

Complete voice interface with superior Brazilian Portuguese understanding and automatic 设置up.

🌟 Key Features Superior PT-BR Understanding 模型: wav2vec2-large-xlsr-53-portuguese (jonatasgrosman) Excellence in: Brazilian Portuguese with slang, expressions, accents Also supports: English (multilingual) 质量: 状态-of-the-art for PT-BR ASR 🤖 Optional Claude Integration Intelligent 响应s using Claude API Falls back to OpenClaw 代理 automatically Optional: No API key required, still works with OpenClaw 代理 Smart: Better understanding of 上下文 and Portuguese nuances Neural Voice Options (Piper TTS) Voice Gender 质量 Character jeff Masculina Medium Clear, professional cadu Masculina Medium Warm, natural faber Masculina Medium Balanced miro Feminina High Community voice Voice Commands

Change voice anytime with:

/voz jeff - Voice: Jeff /voz cadu - Voice: Cadu /voz faber - Voice: Faber /voz miro - Voice: Miro (feminina) /voz feminina - Automatic: miro /voz masculina - Automatic: jeff /voz 列出ar - Show all voices ⚡ 安装ation (NEW!) One-Command 安装ation bash 安装.sh

The 安装er automatically:

✅ 检测s your 系统 architecture (ARM64, x86_64) ✅ 下载s Piper TTS ✅ 下载s 4 Brazilian Portuguese voice 模型s (~240MB) ✅ 安装s Python dependencies ✅ 验证s everything works

No manual 下载s. No configuration. Just one command!

🔄 Critical Rules

DEFAULT: AUDIO ONLY - NO TEXT

When user 发送s audio:

❌ NO transcription shown ❌ NO "Pesquisando...", "Gerando..." ❌ NO confirmations or explanations ✅ ONLY audio reply

TEXT MODE: Say "texto" or "响应a em texto" explicitly

📊 工作流 🎤 Audio 接收d (PT-BR/EN) ↓ 🔤 Transcribe (wav2vec2 PT-BR - silent) ↓ 🤖 AI 响应 (Claude API or OpenClaw 代理 - silent) ↓ 🗣️ Synthesize (Piper neural - silent) ↓ 📤 发送 Audio Reply (silent)

📁 Scripts 安装ation & 设置up 安装.sh - Automatic 安装ation (运行 once!) 健康_检查.py - 验证 the 安装ation Core Processing transcribe.py - wav2vec2 PT-BR speech recognition synthesize.py - Piper TTS with voice selection voice_config.py - Voice preference management process.sh - Full 工作流 orchestration AI Integration claude_adapter.py - Claude API bridge (intelligent 响应s) 🔧 Configuration Optional: Enable Claude Integration

For intelligent AI 响应s, 设置 your API key:

导出 ANTHROPIC_API_KEY="sk-your-API-key"

Without this, the 技能 uses OpenClaw's 代理 (still great 响应s!).

Voice Configuration

Current voice is saved automatically in:

~/.OpenClaw/workspace/.audio_pt_voice_config

📊 Technical DetAIls ASR 模型 Name: jonatasgrosman/wav2vec2-large-xlsr-53-portuguese TrAIning: Fine-调优d on PT-BR Common Voice + other data设置s Strengths: Brazilian slang, regional expressions, 信息rmal speech License: Apache 2.0 TTS Engine Engine: Piper (fast, local neural TTS) Voices: 4 PT-BR options Speed: Real-time on ARM64/x64 格式化: Opus OGG (Telegram 优化d) License: MIT AI 响应 (Optional) Primary: Claude API (when API key provided) Fallback: OpenClaw 代理 (always avAIlable) License: Claude API is proprietary; OpenClaw 代理 is included 🚀 获取ting 启动ed 安装 技能 from ClawHub 运行: bash 安装.sh Re启动: OpenClaw gateway re启动 Use: 发送 audio messages, use /voz commands 📋 Requirements OpenClaw 2026.4.10+ Python 3.8+ 300MB free disk space (for voice 模型s) Internet connection (for initial 下载s) Optional: ANTHROPIC_API_KEY for Claude integration 🔒 隐私 & Security ✅ Audio transcription h应用ens locally (wav2vec2 运行s on your machine) ✅ Voice synthesis h应用ens locally (Piper 运行s on your machine) ⚠️ AI 响应s: Without API key: Processed by OpenClaw 代理 (检查 OpenClaw 隐私) With API key: Sent to Anthropic (Claude respects prompt 隐私 per TOS) 📜 License

MIT - Free to use, modify, and redistribute

🙏 Credits ASR: jonatasgrosman/wav2vec2-large-xlsr-53-portuguese TTS: Piper by Rhasspy AI: Claude API by Anthropic (optional) Voices: Piper Voices 仓库 + TarcisoAmorim community contribution