菜单
Build voice-enabled AI applications with speech recognition, text-to-speech, and voice-based interactions. Supports multiple voice providers and real-time processing. Use when creating voice assistants, voice-controlled applications, audio interfaces, or hands-free AI systems.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Build autonomous game-playing agents using AI and reinforcement learning. Covers game environments, agent decision-making, strategy development, and performance optimization. Use when creating game-playing bots, testing game AI, strategic decision-making systems, or game theory applications.
Build interactive chat agents for exploring and discussing academic research papers from ArXiv. Covers paper retrieval, content processing, question-answering, and research synthesis. Use when building research assistants, paper summarization tools, academic knowledge bases, or scientific literature chatbots.
Build agents that generate creative content including music, memes, podcasts, and multimedia. Covers generative models, content synthesis, style transfer, and creative control. Use when building creative assistants, automated content creators, multimedia generators, or artistic AI systems.
Build agents specialized in conducting thorough research, gathering information from multiple sources, and synthesizing findings. Covers research planning, source evaluation, and report generation. Use when automating market research, competitive analysis, literature reviews, or intelligence gathering.
Build chat interfaces for querying documents using natural language. Extract information from PDFs, GitHub repositories, emails, and other sources. Use when creating interactive document Q&A systems, knowledge base chatbots, email search interfaces, or document exploration tools.
Create agents for financial analysis, investment research, and portfolio management. Covers financial data processing, risk analysis, and recommendation generation. Use when building investment analysis tools, robo-advisors, portfolio trackers, or financial intelligence systems.
| name | voice-ai-integration |
| description | Build voice-enabled AI applications with speech recognition, text-to-speech, and voice-based interactions. Supports multiple voice providers and real-time processing. Use when creating voice assistants, voice-controlled applications, audio interfaces, or hands-free AI systems. |
Build intelligent voice-enabled AI applications that understand spoken language and respond naturally through audio, creating seamless voice-first user experiences.
Voice AI systems combine three key capabilities:
See examples/speech_recognition_providers.py for implementations:
See examples/text_to_speech_providers.py for implementations:
See examples/voice_assistant.py for VoiceAssistant:
See examples/realtime_voice_processor.py for RealTimeVoiceProcessor:
class SmartHomeVoiceAgent:
def __init__(self):
self.voice_assistant = VoiceAssistant()
self.devices = {
"lights": SmartLights(),
"temperature": SmartThermostat(),
"security": SecuritySystem()
}
async def handle_voice_command(self, audio_input):
# Get text from voice
command_text = await self.voice_assistant.process_voice_input(audio_input)
# Parse intent
intent = parse_smart_home_intent(command_text)
# Execute command
if intent.action == "turn_on_lights":
self.devices["lights"].turn_on(intent.room)
elif intent.action == "set_temperature":
self.devices["temperature"].set(intent.value)
# Confirm with voice
response = f"I've {intent.action_description}"
audio_output = await self.voice_assistant.synthesize_response(response)
return audio_output
class VoiceMeetingRecorder:
def __init__(self):
self.processor = RealTimeVoiceProcessor()
self.transcripts = []
async def record_and_transcribe_meeting(self, duration_seconds=3600):
audio_stream = self.processor.stream_audio_input()
buffer = []
chunk_duration = 30 # Transcribe every 30 seconds
for audio_chunk in audio_stream:
buffer.append(audio_chunk)
if sum(len(chunk) for chunk in buffer) >= chunk_duration * 16000:
# Transcribe chunk
transcript = transcribe_audio_whisper(buffer)
self.transcripts.append({
"timestamp": datetime.now(),
"text": transcript
})
buffer = []
return self.transcripts
Solutions:
Solutions:
Solutions: