# Send Local Voice (FluidAudio TTS/STT) to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install
```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing
```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
"schemaVersion": "1.0",
"item": {
"slug": "local-voice",
"name": "Local Voice (FluidAudio TTS/STT)",
"source": "tencent",
"type": "skill",
"category": "AI 智能",
"sourceUrl": "https://clawhub.ai/TrondW/local-voice",
"canonicalUrl": "https://clawhub.ai/TrondW/local-voice",
"targetPlatform": "OpenClaw"
},
"install": {
"downloadUrl": "/downloads/local-voice",
"sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=local-voice",
"sourcePlatform": "tencent",
"targetPlatform": "OpenClaw",
"packageFormat": "ZIP package",
"primaryDoc": "SKILL.md",
"includedAssets": [
"SKILL.md",
"references/VOICES.md",
"scripts/setup.sh",
"scripts/stella-tts.sh",
"sources/Package.swift",
"sources/Sources/StellaVoice/main.swift"
],
"downloadMode": "redirect",
"sourceHealth": {
"source": "tencent",
"slug": "local-voice",
"status": "healthy",
"reason": "direct_download_ok",
"recommendedAction": "download",
"checkedAt": "2026-05-02T06:00:27.224Z",
"expiresAt": "2026-05-09T06:00:27.224Z",
"httpStatus": 200,
"finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=local-voice",
"contentType": "application/zip",
"probeMethod": "head",
"details": {
"probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=local-voice",
"contentDisposition": "attachment; filename=\"local-voice-1.0.1.zip\"",
"redirectLocation": null,
"bodySnippet": null,
"slug": "local-voice"
},
"scope": "item",
"summary": "Item download looks usable.",
"detail": "Yavira can redirect you to the upstream package for this item.",
"primaryActionLabel": "Download for OpenClaw",
"primaryActionHref": "/downloads/local-voice"
},
"validation": {
"installChecklist": [
"Use the Yavira download entry.",
"Review SKILL.md after the package is downloaded.",
"Confirm the extracted package contains the expected setup assets."
],
"postInstallChecks": [
"Confirm the extracted package includes the expected docs or setup files.",
"Validate the skill or prompts are available in your target agent workspace.",
"Capture any manual follow-up steps the agent could not complete."
]
}
},
"links": {
"detailUrl": "https://openagent3.xyz/skills/local-voice",
"downloadUrl": "https://openagent3.xyz/downloads/local-voice",
"agentUrl": "https://openagent3.xyz/skills/local-voice/agent",
"manifestUrl": "https://openagent3.xyz/skills/local-voice/agent.json",
"briefUrl": "https://openagent3.xyz/skills/local-voice/agent.md"
}
}
```
## Documentation
### Local Voice (FluidAudio TTS/STT)
Sub-second local voice AI for Apple Silicon Macs using FluidAudio's CoreML models.
### Features
TTS: Kokoro model with 54 voices, ~0.6-0.8s latency
STT: Parakeet TDT v3, ~0.2-0.3s latency, 25 languages
100% local: No cloud, no cost, works offline
Neural Engine: Runs on Apple's ANE for efficiency
### Requirements
macOS 14+ on Apple Silicon (M1/M2/M3/M4)
Swift 5.9+
espeak-ng (for TTS phoneme fallback)
### 1. Install Dependencies
brew install espeak-ng
### 2. Build the Daemon
cd /path/to/skill/sources
swift build -c release
### 3. Install Binary and Framework
mkdir -p ~/clawd/bin
cp .build/release/StellaVoice ~/clawd/bin/
cp -R .build/arm64-apple-macosx/release/ESpeakNG.framework ~/clawd/bin/
install_name_tool -add_rpath @executable_path ~/clawd/bin/StellaVoice
### 4. Create LaunchAgent
cat > ~/Library/LaunchAgents/com.stella.tts.plist << 'EOF'
Label
com.stella.tts
ProgramArguments
$HOME/clawd/bin/StellaVoice
RunAtLoad
KeepAlive
StandardOutPath
$HOME/.clawdbot/logs/stella-tts.log
StandardErrorPath
$HOME/.clawdbot/logs/stella-tts.err.log
EOF
launchctl load ~/Library/LaunchAgents/com.stella.tts.plist
### API Endpoints
The daemon listens on http://127.0.0.1:18790:
### TTS - Text to Speech
# Simple text to WAV
curl -X POST http://127.0.0.1:18790/synthesize -d "Hello world" -o output.wav
# With speed control (0.5-2.0)
curl -X POST "http://127.0.0.1:18790/synthesize?speed=1.2" -d "Fast!" -o output.wav
# JSON endpoint
curl -X POST http://127.0.0.1:18790/synthesize/json \\
-H "Content-Type: application/json" \\
-d '{"text": "Hello", "speed": 1.0, "deEss": true}'
### STT - Speech to Text
curl -X POST http://127.0.0.1:18790/transcribe \\
--data-binary @audio.wav \\
-H "Content-Type: audio/wav"
# Returns: {"text": "transcribed text"}
### Health Check
curl http://127.0.0.1:18790/health
# Returns: ok
### Voice Options
Default voice is af_sky. Change by modifying the source code.
Top Kokoro voices (American female):
af_heart (A grade) - warm, natural
af_bella (A-) - expressive
af_sky (C-) - clear, light
All 54 voices: See references/VOICES.md
### Speed Control
speed=0.8 → Calm, relaxed
speed=1.0 → Natural pace
speed=1.2 → Energetic, upbeat
### Punctuation (automatic)
! → Excited tone
? → Rising intonation
. → Neutral, falling
... → Pauses
### SSML Tags
Kokoro
Dr.
2024-01-15
### Helper Script
See scripts/stella-tts.sh for a convenient wrapper:
scripts/stella-tts.sh "Hello world" output.wav
scripts/stella-tts.sh "Hello world" output.mp3 # Auto-converts
### Integration Example
For voice assistants, update your voice proxy to use local endpoints:
// STT
const response = await fetch('http://127.0.0.1:18790/transcribe', {
method: 'POST',
headers: { 'Content-Type': 'audio/wav' },
body: audioData
});
const { text } = await response.json();
// TTS
const audio = await fetch('http://127.0.0.1:18790/synthesize', {
method: 'POST',
body: textToSpeak
});
### Troubleshooting
Library not loaded (ESpeakNG)
Ensure ESpeakNG.framework is in the same directory as the binary
Run install_name_tool -add_rpath @executable_path /path/to/binary
Slow first request
First request loads models (~8-10s)
Subsequent requests are sub-second
x86 vs ARM
Must build and run on ARM64 native (not Rosetta)
Check with uname -m (should show arm64)
### Source Code
The daemon source is in sources/ directory. It's a Swift package using:
FluidAudio (TTS + STT models)
Hummingbird (HTTP server)
Rebuild after modifying:
cd sources && swift build -c release
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: TrondW
- Version: 1.0.1
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-02T06:00:27.224Z
- Expires at: 2026-05-09T06:00:27.224Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/local-voice)
- [Send to Agent page](https://openagent3.xyz/skills/local-voice/agent)
- [JSON manifest](https://openagent3.xyz/skills/local-voice/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/local-voice/agent.md)
- [Download page](https://openagent3.xyz/downloads/local-voice)