Voice Agent Engineer, Aksel AI skill by KissMySkills, cover

Voice Agent Engineer AI Skill - Aksel

$19
Skip to product information
Voice Agent Engineer, Aksel AI skill by KissMySkills, cover

Voice Agent Engineer AI Skill - Aksel

Build low-latency voice agents: streaming STT-LLM-TTS, barge-in, a latency budget and measured WER.

$19 this skill one payment yours forever

Claude skill package instant downloadaksel-voice-realtime-agent-engineer.skill

Library plan

Get this skill and 2,500+ others

$9/mo or $59 a year

Get Library · $9/moGet Library
Try this skill free for 7 daysTry this skill free

Nothing is charged. A −30% code for your first payment arrives 2 days before the trial ends.

  • Works inside Claude, ChatGPT, Claude Code, Codex and Cursor through one connector
  • Every skill, prompt pack and agent, plus AI CRM and tools during the trial
  • Cancel anytime
Why a subscription? How it works

Need just this skill?

One file, paid once. No updates, no connector.

Costs about the same as 2 months of Library.

$19

Pay once, keep foreverInstant download30-day money-back guarantee

As featured onProduct HuntFazierKittyLaunch

  • Visa
  • Mastercard
  • American Express
  • Apple Pay
  • BLIK
  • Klarna

Secure checkout by Stripe

Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.

How it works

Ask it something hard.

📎 aksel-voice-realtime-agent-engineer.skillLOADED ✓
Voice agent demo: responses take 2.5s and users constantly talk over the bot. Where does the latency budget actually go?
CLAUDE · WITH THIS SKILL 2.5s means the pipeline runs sequentially - budget it: VAD and endpointing 100-200ms, streaming STT partials about 150ms, LLM TTFT 300-400ms, TTS first-audio 150-250ms; streamed and overlapped that lands at 700-900ms perceived, where talking over the bot mostly stops. Fixes in order: stream every stage, start TTS on the first sentence, and implement real barge-in - detect user speech and kill playback within 100ms. Also tune endpointing: 800ms of trailing silence reads as slow, 300-400ms reads as attentive. Which stack - a realtime speech API or your own STT-LLM-TTS chain?

Or have every skill inside your AI.

0:16 · no sound
Get all 2,500+ with Library · $9/mo →

Questions before you buy? A person answers, usually the same day: hello@kissmyskills.com

// the file itself

Read it before you buy it.

The first lines of the file your AI will read, exactly as delivered. Nothing rewritten for the page.

Use the name
Once the file is loaded, talk to it by name: “Serge, check this page.” That is what the name is for. It also keeps several skills apart in one chat.
// the skill your AI runs on

You are Aksel, a Senior Voice and Realtime Agent Engineer whose north star is that latency is the product: sub-800 ms to first audio, streaming everything, barge-in within 150 ms. You have been activated to build a fast spoken agent.

SKILL.md · 235 lines · instant download

// what's inside

What's inside this skill

  1. The realtime STT-LLM-TTS pipeline and a per-stage latency budget
  2. Turn-taking: VAD, endpointing and barge-in handling
  3. Telephony vs web (SIP, WebRTC) and mid-call tool calls
  4. Evaluation: latency percentiles, word error rate, task success

Teams building phone or voice agents who need sub-second, natural, interruptible conversations.

// two ways to get it

Use it inside your AI, or download it once.

Library plan

This skill and 2,500+ others, inside your chat

$9/mo cancel anytime, or $59 a year

  • All 2,500+ skills, prompt packs and agents, loaded the moment you ask
  • Nothing to download or paste: connect once in Claude, ChatGPT, Claude Code or Cursor
  • New skills every week and 10 catalog files a month to download
Compare Library, AI CRM and Both
Buy once

Just this skill, as a file

$19 one payment

  • Download after checkout and paste it into any AI chat
  • One file, no updates, no connector
  • 30-day money-back guarantee

Already on Library or Both? This one is included, no need to buy the file.

// ask your assistant

Or let your AI set up this skill for you.

Go to kissmyskills.com/pages/connector and set up the "Voice Agent Engineer AI Skill - Aksel" skill (handle: aksel-voice-realtime-agent-engineer) for me

Paste it into Claude, ChatGPT, Claude Code, Cursor or Codex. Your AI walks you through connecting KissMySkills (about 3 minutes, 7-day free trial) and loads the skill. What your AI will read →

What you're actually buying

Drop Aksel into Claude and get a senior voice AI engineer who builds low-latency realtime agents where latency is the product.

Aksel builds voice and realtime agents: the STT to LLM to TTS pipeline (and speech-to-speech realtime APIs), the latency budget (sub-800ms target broken down across VAD, endpointing, STT, LLM TTFT, TTS first-audio and network), streaming everything, turn-taking (voice activity detection, endpointing, barge-in and interruption), telephony vs web (SIP, WebRTC, codecs), mid-conversation tool calls, error recovery, and evaluation (latency percentiles, word error rate, task success). Tools like Deepgram, Whisper, ElevenLabs, Cartesia, LiveKit, Pipecat and the OpenAI Realtime API, without lock-in. Test in staging under real network conditions before production.

What you get

  • →The realtime STT-LLM-TTS pipeline and a per-stage latency budget
  • →Turn-taking: VAD, endpointing and barge-in handling
  • →Telephony vs web (SIP, WebRTC) and mid-call tool calls
  • →Evaluation: latency percentiles, word error rate, task success
📄 aksel-voice-realtime-agent-engineer.skill Under 2 min install Works with Claude, ChatGPT & any AI chat

How to install

Download the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Aksel builds the answer. Includes a full worked example so you see exactly what you get.

// how to install Under 2 minutes

Four steps. Any AI chat.

  1. 01
    Download the file

    After checkout, the download link lands in your inbox. Save the .skill file: Claude takes it as it is.

  2. 02
    Open your AI chat

    Any AI chat you already use: Claude, ChatGPT, Gemini, Grok, Copilot or another.

  3. 03
    Add it to your AI

    Claude: Settings → Capabilities → Skills, upload the .skill file. ChatGPT, Gemini and others: open the .skill file like a .zip archive and paste SKILL.md into custom instructions or Project instructions.

  4. 04
    Start working

    Your AI is now configured as a specialist. Ask it anything inside its domain.

No technical knowledge required.

With Library there is nothing to download. Connect your AI once, then just ask: "Load Voice Agent Engineer AI Skill from KissMySkills."

Setup guide → Library · $9/mo →

// faq

Questions about this product

What does the Aksel skill do?+

Build low-latency voice agents: streaming STT-LLM-TTS, barge-in, a latency budget and measured WER. Load it once into Claude Projects and you get a configured Voice & Realtime Agent Engineer without re-explaining context at the start of every session. Build and evaluate against a held-out test set in a development or staging environment, add guardrails, cost and rate limits, and human review, and roll out behind evals and monitoring before serving agents or LLM features in production.

How do I install this skill file?+

Download the .skill package (it contains SKILL.md), paste the contents into Claude Projects Instructions or your AI's system prompt, add your own context and start your first session. Works with Claude, ChatGPT, or any AI chat that accepts system prompts.

Which AI tools does this skill work with?+

Works with Claude (recommended), ChatGPT, Gemini, Perplexity and Copilot, and any AI chat that accepts system prompts. Claude Projects gives the best results.

How is this different from using Claude without the Aksel skill?+

Without a skill file your AI starts every session as a general assistant. With Aksel loaded it applies Voice & Realtime Agent Engineer methodology from the first message, with consistent quality every time. Build and evaluate against a held-out test set in a development or staging environment, add guardrails, cost and rate limits, and human review, and roll out behind evals and monitoring before serving agents or LLM features in production.

Ready to give your AI a specialist?

This one and 2,500+ others, inside Claude, ChatGPT, Claude Code, Codex or Cursor. Cancel anytime.