Freelance Avatar Rigging & Lip Sync Specialist

Freelance Opportunity: Avatar Rigging & Lip Sync Specialist (Custom GLB + Azure Speech Viseme Pipeline)

We’re looking for a freelance Avatar Rigging & Lip Sync Specialist to support the development of our AI-powered language learning platform, Talkida.

Important — what this project is (and isn’t)

This role is for custom GLB avatars rendered in a React Native + Three.js viewer, with lip sync driven by Azure Speech viseme IDs (0–21) delivered over WebRTC.

This is not Microsoft’s hosted Azure AI Avatar video service (e.g. standard/photo avatars streamed as video). We do not need custom rig export into the Azure AI Avatar SDK — that would be the wrong expectation for this engagement.

Project Scope

We currently have 10 AI avatar drafts that require professional refinement and optimization for production use.

The selected freelancer will be responsible for:

✅ Character rigging and skeleton optimization

✅ Facial rigging and blendshape adjustments

✅ High-quality lip sync setup and calibration

✅ Avatar animation readiness for AI-generated speech workflows

✅ Ensuring compatibility with our Azure Speech viseme (0–21) pipeline and GLB delivery standards

✅ glTF/GLB editing, testing, and export processes (Blender or equivalent DCC workflow)

✅ Improving avatar realism, facial expressions, and speech synchronization

Delivery reference: Production-quality targets align with our Fischer/Carter standard (viseme_* morphs + jawOpen, meter-scale export, live speech QA).

Required Skills

Advanced experience with character rigging and facial blendshape systems

Strong background in lip sync / viseme-based animation workflows

Experience preparing avatars for real-time, speech-driven playback (not pre-rendered video avatars)

Ability to deliver production-ready GLB assets that work in a Three.js morph-target viewer

Knowledge of Azure Speech viseme IDs (0–21) or equivalent phoneme-to-blendshape mapping

Understanding of avatar pipelines used in conversational AI / language-learning products

Portfolio demonstrating previous avatar, character, or metahuman-related projects

Nice to Have

Blender + glTF export experience (helpful, not mandatory — CC3/iClone or other DCC pipelines are acceptable if export meets our spec)

Experience with AI-powered / real-time facial animation systems

Familiarity with WebRTC or low-latency speech sync constraints

Experience with educational or conversational AI products

Project Details

Remote / Freelance

Project-based engagement

10 avatar models to be refined and prepared for production

If you’ve worked on custom 3D avatar pipelines — rigging, visemes, lip sync, GLB export, and real-time speech sync — we’d love to hear from you.

Please share:

Portfolio (include at least one real-time / viseme-driven lip sync example if possible)

Relevant projects (tooling: Blender, CC3, iClone, etc.)

Availability

Expected project fee (ideally per-avatar or milestone breakdown)

Email on mustafa@meet2talk.cafe to apply for the position.

Job Types: Part-time, Contract
Contract length: 12 months

Work Location: Remote