Dispatch text-to-speech to an external provider via a speak function and CLI.
npx skills add https://github.com/matt-fell-ai/PAI --skill voice
Please help me install this Agent Skill. Skill: Voice Source: https://github.com/matt-fell-ai/PAI/tree/main/skills/Voice Command: npx skills add https://github.com/matt-fell-ai/PAI --skill voice
This Skill adds modular voice capabilities to the PAI, enabling hands-free interaction, accessibility, and natural language communication with the system.
pai run Voice speak "Hello world"
High-intent search queries and answers about installing and using this skill.
Text-to-speech voice output converts AI responses into spoken audio through external TTS providers. Use the Voice Skill's speak function to dispatch text and trigger real-time voice playback, enabling hands-free interaction and accessibility for chat-to-voice workflows.
Yes. Voice-input accessibility lets users interact with the PAI via spoken commands to trigger actions hands-free. The Skill provides modular voice capabilities for real-time voice I/O, supporting both voice input and text-to-speech output for natural language communication.
The Voice Skill implements a modular speak function that dispatches text-to-speech to an external provider with a CLI trigger. Deploy it instantly using `pai run Voice speak "text"` to add real-time spoken feedback and status announcements to AI systems.
Yes. The Skill delivers AI feedback and spoken responses for accessibility and hands-free operation. It supports voice-enabled alerts, status announcements, and demonstrations, making it suitable for systems requiring real-time spoken output across AI assistants.
Access to an external text-to-speech provider is the core requirement. The Voice Skill has no internal dependencies—it's modular and can be integrated directly into existing AI systems to add voice capabilities to chat workflows and demonstrations.
GeneralReasoningConvert text into speech using OpenAI's TTS API with configurable voices and models.
wwloreySynthesize spoken audio from text for playback or WAV/MP3 files.
microsoftEnable real-time bidirectional voice conversations between Java applications and AI assistants.
blueskies1818Transcribe speech and identify languages in 99 languages using OpenAI Whisper.
