The voice library — human-sounding synthetic speech, filterable by language and accent, and clonable from your own audio.
Pick this whenThe voice itself is the product decision: you want a specific accent, gender or a cloned voice rather than a stock one.
What makes it different
Filterable library (English, British, male…) with a voice ID you paste straight into Retell
Voice cloning from roughly 20 minutes of audio
Multilingual voice tags for agents that must switch language
What it does
Generates human-like speech in many voices and languages
Supplies voice IDs to voice-agent platforms as a custom provider
Clones a voice from a sample
What it does not do
Common wrong expectationsDoesn't build the agent — it supplies the voice the agent speaks in
Where it sits in a stack
The voice layer of any phone or audio agent; billing unifies with the platform that calls it.
Our status · not-usingNo audio work in scope.
For your projectsNone currently — though a spoken summary of a session page is a plausible accessibility idea if audio ever becomes interesting.
| Session | Coverage | Moment | What happened |
|---|
| Basecamp 6: Voice Agents | demonstrated | 1:09:54 | Voice library filtering (English/British/male), voice ID copy into Retell custom provider, multilingual voice tags, voice cloning (~20 min audio) per his LinkedIn video |
| Session 13: Claude Code — Skills, Sub Agents & the Token Economy (posted as 'Beyond Vibe Coding — n8n & More') | demonstrated | 2:06:54 | Voice-over via restricted key in .env; free-tier commercial-rights limit flagged by Claude |
| Day 6: Voice Agents That Talk Like Humans — the 5-Step Pipeline, Retell Settings That Matter, the 5-Section Prompt, cal.com Booking, and Call Logging | demonstrated | | Voice import by Voice ID; TTS cost share |
| Day 8: AI Workflows — Chaining Tools, the IDEA(L) Analysis Framework, Claude Skills vs MCP vs Projects, and the Reel-Cloning Pipeline | demonstrated | | IVC vs PVC; v3 alpha audio tags test; multilingual v2 |
| Day 2: ACR and DRA Thinking Frameworks, Connectors and Scheduled Tasks, the Image-to-Video Ad Pipeline, MoSCoW + 5 Whys, and Building LearnVault Back-End-First in Lovable | demonstrated | | Voice-over |
| Sections 4-5: AI Clones and AI Video — the 5-Step Workflow, Image-to-Video Prompting, First/Last Frame, HeyGen, Runway Aleph, ElevenLabs Voice, and Wan 2.2 Replace | demonstrated | | TTS, clone, Voice Changer |
| Section 6: Four Full Builds — a Faceless Hook in 20 Minutes, a '$300,000 Ad for Under $30', an Animated Music Video, and a Viral AI-Clone Action Sequence | demonstrated | | V3 director cues; Voice Changer; SFX tab |
| Section 9: AI Video Editing — the Same Edit in DaVinci and CapCut, Ten DaVinci AI Tools, Premiere's Generative Features, SubMagic, Autopod, Adobe Enhance, Voice-Clone ADR, and Horizontal-to-Vertical Outpainting | demonstrated | | Professional Voice Clone for ADR |
| Supplement: The Realtor Reel Pipeline, Twenty-Five AI Filmmaking Moves, and Five Editors Graded Out of Ten | demonstrated | | Dubbing into other languages and voice changing; PromptEdit does not dub |
| Build Your AI Twin: Clone Your Face on HeyGen and Your Voice on ElevenLabs (Instant vs Professional Cloning) | demonstrated | | Instant vs professional cloning; TTS settings; ~$11/$22 |
| Connect the Dots: Link ElevenLabs to HeyGen by API Key, Produce Your First Avatar Video, Fix Pronunciation, and the External-Audio Workaround | demonstrated | | API key; TTS download |
| Founder Stack Ep03 with Shai Krishna: Why Wrappers Make AI Slop - CLAUDE.md as the Brain and DESIGN.md as the Art Direction, Founder-Led UGC with AI Avatars, Trial Reels, and Email Journeys | explained | 1:33:00 | 70-80 percent voice match |
| AI Sprint: Windsurf & Devin — Day 1 (Vibe to Agentic: GitHub as Pizza, the Four Spec Concerns, and the IDE Lineage) | explained | | The agent-friendly documentation exhibit: copy-page, open-in-Claude/ChatGPT/Cursor buttons |
| Basecamp 1: Prompting & RAGs | mentioned | 0:31:18 | Human-like generated voices |
| Community Session II: The Meta-Harness — Praful Thakkar on AgentGrid, Orchestrator-plus-Workers on One Canvas, Hand-Off Between Models, and OAuth Instead of API Keys | mentioned | | Voice via Wixie |
| Office Hours II: When to Pay for Vercel, Scraping Public Data for Paul's Gold-Pressure App, Audits as a Sales Hook, and Why Distribution Beats Building | mentioned | | Voice layer on Stephen's SAP HCM product |
| Session 9: Introduction to Cursor & its principles | mentioned | 1:15:51 | The audio-skills MCP answer — with a token-cost warning |
| Session 14: Claude Code — Advanced Workflows | mentioned | 2:58:55 | Abandoned at the paywall in favor of macOS TTS |
| Session 16: GitHub 101 — Fundamentals & Essentials | mentioned | 1:23:06 | Floated for escape-room audio, not used (ASR: '11 Labs') |
| Session 18: Nano Banana + Veo 3.1 Multi-Shot Video — UGC Genie, an AI-UGC Product Built Live | mentioned | | Voice lane for the client-likeness ads question |
| Day 2: The Image/Video Model Landscape, Cinematic Prompting, Cost Strategy, and a Commercial Built Live | mentioned | | Voice + music; not demoed for time |
| Pillar 2 - Your Specialty: Own One Thing, the Specificity Formula, and the 'Get Ultra Specific' Interrogation Workflow | mentioned | | |
| The Five-Level AI Generalist Roadmap (+ Operating System & Monetization) | mentioned | | Voice generation across L1 starter stack and L3 audio (with Whisper, Suno, Udio, AssemblyAI) |
| Learning Topics: Sessions 1–5 — Foundations to AI Director | mentioned | | Audio synthesis in the session-5 directory; voice-cloning consent rule attached |
| Day 2 (afternoon): MCP as the USB Port for AI, Building a Server in Two Lines, the Four Orchestration Shapes, and CRUD as the Security Model | mentioned | | Paid MCP example |
| AI Sprint: OpenClaw — Session 2 (Token Anatomy, Claude Code Inside the Server, Skills, and Multi-Agent Workspaces) | mentioned | | The voice-skill category's obvious ingredient |
ElevenLabs