Tts
Personal Ai Agent
npx -y skills add br3eze-code/br3eze-code --skill ttsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.2 KB, as published. Nobody here has run it
Skill: tts
Version: 1.0.0
Domain: audio
Description
Text-to-speech synthesis with multiple provider backends. Converts operator messages, AI responses, or status reports to audio. Supports streaming and voice listing.
When to Use
Invoke when the user asks about:
- Converting text or a report to audio/speech
- Generating voice announcements for community broadcasts
- Listing available voices from a provider
- Streaming speech in real time
Tools
| Action | Description |
|---|---|
synthesize | Convert text to audio file (mp3/wav/ogg/opus) |
stream | Stream audio in real time |
voices | List available voices for the selected provider |
Providers
| Provider | Description |
|---|---|
edge (default) | Microsoft Edge TTS (free, no API key) |
openai | OpenAI TTS API |
elevenlabs | ElevenLabs high-quality voices |
google | Google Cloud Text-to-Speech |
local | Local offline TTS engine |
Example: Synthesize
{
"action": "synthesize",
"provider": "edge",
"text": "AgentOS: System health check complete. All systems nominal.",
"voice": "en-ZA-LukeNeural",
"speed": 1.0,
"format": "mp3",
"language": "en"
}
Permissions
audio:synthesize— required for all TTS actions