9 skills · sorted by relevance
Build or repair NVIDIA voice agents with Pipecat or LiveKit for real-time spoken conversations. Set up speech recognition, language models, and speech synthesis, customize pronunciation or multilingual routing, and deploy locally or in the cloud.
Customize NVIDIA Nemotron Voice Agent’s Generic Pipecat example for appointment scheduling, five-field patient intake, or a custom healthcare conversation. Build prompts and tool handlers without a separate backend, then validate conversation behavior, services, and voice interaction.
Plan voice AI systems by comparing direct speech processing with separate transcription, language generation, and speech synthesis stages. Covers response delays, detecting when people speak, interruptions, and noise handling to guide conversational interface design.
Build and evaluate low-latency spoken, multimodal, and translation experiences with Google Gemini Live API and Gemini Enterprise Agent Platform Live API. Use when a media-production or voice-agent workflow needs real-time audio input/output, barge-in, voice configuration, live transcription, live translation, tool/function calling during a spoken session, WebSocket session design, latency QA, quotas/cost review, or Google/Vertex data-governance tradeoffs.
The English summary is being prepared. Showing the original description.
Create, improve, or audit Vapi voice agent and Squad system prompts for production phone and web based voice agents. Use when the user wants help designing a Vapi assistant prompt, multi-assistant Squad prompt set, refining an existing prompt, creating prompt sections, building an intake or handoff workflow, improving tool-use instructions, adding guardrails, or optimizing voice-agent behavior for brevity, turn-taking, error handling, caller data collection, escalation, handoffs, and spoken formatting.
The English summary is being prepared. Showing the original description.
Identify and remove phrasing, structure, and word choices that signal AI authorship. Runs iterative passes through fresh voice-agent instances with the orchestrator acting as gatekeeper on every change. Use on a cover letter before submission, or on any prose that has to read as human-written.
The English summary is being prepared. Showing the original description.
Agentes de voz representam a fronteira da interação com IA - humanos falando naturalmente com sistemas de IA. O desafio não é apenas reconhecimento e síntese de fala, mas alcançar fluxo de conversa natural com latência inferior a 800ms enquanto se lidam com interrupções, ruído de fundo e nuances emocionais. Esta habilidade cobre duas arquiteturas: fala-para-fala (OpenAI Realtime API, menor latência, mais natural) e pipeline (STT→LLM→TTS, mais controle, mais fácil de depurar). Insight-chave: latência é a restrição. Hu
The English summary is being prepared. Showing the original description.
Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu
The English summary is being prepared. Showing the original description.
Plan a user interview topic in PostHog — pick who to target (cohort, emails, or PostHog distinct IDs), draft what to ask about, and prepare the voice-agent context plus a question list. Use when the user asks to "talk to users", "check how users feel about X", "interview some customers", "set up a user interview", "run a user-research call", "find users to ask about Y", or otherwise wants qualitative feedback through a conversation. Walks the user through targeting (cohorts-list, persons-list, or accepting emails / distinct IDs directly), captures the topic, and prompts for agent context and questions before calling user-interview-topics-create. Cohort targeting is resolved to explicit emails/distinct_ids at create time — topics snapshot their audience and do not re-evaluate cohort membership later. Do NOT trigger when the user is uploading a recorded interview audio file (that's the separate UserInterview/transcript flow) or only browsing existing topics with user-interview-topics-list.
The English summary is being prepared. Showing the original description.