Hire an AI voice AI integration planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A stage-by-stage plan from audio file to finished transcript, with what each stage does
• A choice between local and cloud transcription, with the trade-offs for your case
• Audio clean-up steps, a splitting plan for long files, and speaker-label and subtitle steps
• A privacy and storage checklist for the audio and the text
• Quality checks to run at each stage, and a small test to try before you scale up

How it does the job well

• Never state a word error rate, a time saving or a price as a fact. Say it must be measured or checked.
• Do not give legal or compliance sign-off for HIPAA, GDPR or similar rules. List what to ask a qualified professional.
• Recordings can hold personal and health details. Plan for removal, short storage and no public sharing.
• You cannot remember between chats. Tell the user to save the plan and paste it back next time.
• Read the existing code, its conventions and its tests before changing anything. Match the project's patterns.
• Make the smallest change that fully solves the request. Keep unrelated refactors out.
• Reproduce a bug before fixing it, and add a test that fails without the fix.

Mistakes it avoids

• Claiming code works without running it or its tests.
• Inventing APIs, package versions or settings instead of checking the installed ones.
• Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces.

What a good result looks like

An example, not your task: You have hundreds of interviews, calls or podcast episodes to turn into text and need a plan that scales.

• Goal. Your audio, languages, needed outputs and destination in one short block.
• Pipeline plan. Each stage in order, with what it does, what can go wrong and how to check it.
• Local or cloud. A pick with reasons based on privacy, cost, speed and language coverage.
• Outputs. Each file you get, such as plain text, subtitles or speaker-labelled text, and who uses it.
• Privacy and storage. How audio and text are handled, kept and deleted, and what private data is removed.
• Test plan. Three kinds of recordings to try first and what a pass looks like for each.

How the work is checked

• The changed files build, and the relevant tests and linters pass. The commands and results are shown.
• Each change is explained in one line with its reason, and risky areas are named.
• Any check that could not run is reported as NOT_RUN with what it needs.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Chris Voss would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Set the goal. It confirms what the audio is, what you need out and where it goes, and asks once for what is missing.
• Check the input. It plans file checks for format, length and sound, so bad files are caught before they cost time.
• Prepare the audio. It plans conversion to the format speech models expect, plus clean-up and splitting of long files.
• Choose where to transcribe. It compares a model on your own machine with a cloud service on privacy, cost, speed and languages.
• Label and tidy. It plans speaker labels, punctuation clean-up, time stamps and subtitle files, and flags low-confidence parts for a human.
• Deliver and protect. It plans how the text reaches your tools, how long files are kept and how private data is removed.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id engineering-voice-ai-integration-engineer only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/engineering-voice-ai-integration-engineer/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• What your recordings are, such as support calls, podcasts or interviews, and how long they run
• How many you have, and whether they arrive in batches or one by one
• Languages and accents, and how noisy the audio is
• What you need out, such as plain text, subtitles, speaker labels or action items
• Where the text must go, such as your website, a spreadsheet or a summary tool
• Privacy limits, budget and speed needs (optional)

Helpful context (optional)

• Two or three sample recordings, one clean and one hard, to test the plan on.
• A list of names and special words, such as product names, that must be spelled right.

Tools and access

• Claude, ChatGPT or Gemini: A plan needs only pasted text. Code it writes must be run by you or a developer, with ffmpeg and a speech model installed.

Functions and deliverables

• Voice AI integration planner: Plan a speech-to-text system for your recordings, with the audio prep, tool choice, speaker labels, subtitles, privacy steps and quality checks.
  • A stage-by-stage plan from audio file to finished transcript, with what each stage does
  • A choice between local and cloud transcription, with the trade-offs for your case
  • Audio clean-up steps, a splitting plan for long files, and speaker-label and subtitle steps
  • A privacy and storage checklist for the audio and the text
  • Quality checks to run at each stage, and a small test to try before you scale up
  Source: Michael Sitarzewski and Agency Agents contributors.
• Noisy audio cleaner: Use ElevenLabs Voice Isolator to cut noise. Get speech audio from a file or link.
  • A clean speech audio file
  • Code to run it on more files
  • A faster PCM option for low delay
  Source: ElevenLabs.
• System design planner: Plan your system design before you build. Describe your app and get an architecture pick, a diagram and the trade-offs behind each choice.
  • A recommended architecture
  • A diagram in Mermaid form
  • A dependency check with problems flagged
  • A trade-off summary for each choice
  Source: Alireza Rezvani.
• Negotiation call prep planner: Plan a hard negotiation call with an opening, feeling labels, how and what questions and the facts to learn before you give anything away.
  • An opening that names what they may fear about you
  • Feeling labels and how and what questions
  • A safe-no question and a test for a fast yes
  • A ranked list of facts to find
• AI project context organiser: Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.
  • A ready rules file for your project
  • A list of which files to load for each task
  • Rules for when to reset or trim the session
  • A checklist for spotting drifting answers
  Source: Addy Osmani.
• Chris Voss: Prepare a difficult conversation using Chris Voss’s recorded approach. Summarise the other side, ask calm questions and test how an agreement will work.
  • Your problem worked on the way Chris Voss would: their questions, their method, their push-back
  • The answer or the work, in Chris Voss's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You have hundreds of interviews, calls or podcast episodes to turn into text and need a plan that scales.
• Your transcripts come out garbled on noisy, long or multi-speaker recordings and you do not know which stage is at fault.
• You need subtitles (SRT or VTT) or speaker-labelled text to feed a summary tool or your website.
• You must decide whether private recordings can go to a cloud service or must stay on your own machine.

Limits to check before starting

• You just want one audio file turned into text today: use the Whisper speech transcriber.
• You want a summary and action items from one meeting recording: use the Audio meeting notes writer.
• You want to turn text into speech: use the Voiceover maker.
• You want a video in another language: use the Video dubbing editor.
• You need a legal or medical compliance sign-off for call recordings. A plan is not one: ask a qualified professional.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Add the pack to your AI as a skill. Or open a new chat and paste SKILL.md, then references/source-agent.md.
• Describe your recordings, volume, languages and the output you need. Add any privacy rules, such as "audio may not leave our network".
• Ask for the plan first. Say "Plan only. Do not write code yet." Your AI asks once for anything missing.
• Read the local versus cloud choice and the privacy section before the rest. Fix anything that does not match your rules.
• Ask for code for one stage at a time. You need a person or tool that can run it, such as Python and ffmpeg. A chat AI cannot run it for you.
• Test the plan on three of your own recordings, one clean and two hard. Compare the text to what you hear before you scale up.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/engineering-voice-ai-integration-engineer for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.