Voice AI
Role:
Lead Product Designer
Timeline:
Jun 2023 - Apr 2024
Scope:
UX research, product design, and GTM collaboration
Project Summary
VoiceAI is a web-based AI transcription platform within NeuralSpace’s product suite. It supports real-time and file-based transcription, multilingual speech recognition, and developer APIs for integration.
Impact
30% increase in user adoption post-launch
45% reduction in transcription turnaround time
Expansion across Arabic, Indic, and European languages
Strong internal and external feedback on clarity and usability
The project involved designing a full-fledged product from MVP to scale, balancing AI capability, usability, and market readiness.
Product Demo
Below is a working overview of the VoiceAI platform, showcasing the core user flows across transcription, AI interaction, usage tracking, and developer configuration.
Problem & Constraints
NeuralSpace had strong speech and language models, but product adoption was limited by complexity.
Existing tools primarily targeted technical users
Non-technical users faced onboarding friction
The platform needed to support both users in a single experience
The product had to scale globally and align with an ongoing rebrand
The constraint was not technical feasibility, but clarity and adoption.
Design Strategy
Shipped an MVP to validate workflows before optimizing advanced capabilities
Translated backend and LLM complexity into clear system states
Designed task-based workflows instead of feature-driven interfaces
Used sales and marketing feedback to improve clarity during demos and onboarding
Simplified existing product patterns while staying aligned with the rebrand
MVP Scope
The initial MVP focused on validating core transcription workflows and demand.
Features that were included in the MVP:
Real-time transcription
File-based transcription
Developer APIs and documentation
The MVP established baseline usage and surfaced early friction points across user types.
Insights
Post-MVP insights were gathered through:
Key Insights
Key Design Changes (Post-MVP)
Introduced text-to-speech for transcription reuse
Enabled users to convert text into speech using multiple voices to support accessibility and content reuse.
Added AI-powered querying directly within transcripts
Introduced Ask Me Anything to allow users to ask questions from transcripts and audio without leaving context.
Made upload and processing status visible in real time
Added progress indicators and status updates to reduce uncertainty during file uploads and transcription.
Bringing VoiceAI to the World
Design responsibility extended beyond the product interface to how VoiceAI was introduced and understood externally.
Marketing assets were designed to support product launch, feature announcements, and sales enablement, ensuring the platform’s value was clear to non-technical audiences.
Design Focus
Translate complex AI capabilities into clear, user-facing value
Reduce perceived product complexity
Maintain consistency with the NeuralSpace rebrand across touchpoints
Assets delivered
Feature walkthrough visuals for Text-to-Speech and Ask Me Anything
Social media and launch assets highlighting real-world use cases
Campaign visuals supporting multilingual and dialectal speech recognition
Learnings and Takeaways
This project reinforced my ability to:
Take a technically complex AI system and turn it into workflows people can actually understand and use
Design for both technical and non-technical users without building two separate products
Make product decisions that balance usability, system constraints, and go-to-market needs
Work closely with engineering, product, data science, sales, and marketing to ship and position a real product
Core takeaway: I can design AI products that are grounded in how systems work, but still feel clear, usable, and ready for real-world adoption.