Available on iOS

InnerVoice Mobile

The award-winning app that bridges the gap between virtual and physical worlds—teaching communication in context so skills carry over to real life.

Designed by and for autistic communicators. Universal design that works for any child with communication challenges and delays.

25,000+ downloads
100,000+ sessions
InnerVoice Mobile app showing animated avatar and communication buttons
Built by Experts

Why trust InnerVoice?

Created by speech-language pathologists with 40+ years combined experience, backed by millions in research grants, and recognized by Microsoft, Mensa, and the National Academies of Sciences.

Lois Jean Brady

MS, CCC-SLP, CAS

CEO & Principal Investigator

  • 30+ years as a Speech-Language Pathologist
  • Author of "Apps for Autism" and 4 other books
  • Publisher of Autism Digest magazine
  • Board of Directors, US-SAAC
  • Certified Animal-Assisted Therapy practitioner

Matthew Guggemos

MS, CCC-SLP

CTO & Research Director

  • AI & Speech Technology innovator
  • Board Member, American Society for AI
  • Invited Speaker, National Academies (AI & Neuroscience)
  • Guest Editor, Mensa Research Journal
  • Co-publisher of Autism Digest

Mensa Award

2013 Intellectual Benefits

Microsoft

AI for Accessibility

NSF Grants

Phase I & II SBIR

NIH Grants

R43 Research

Backed by NSF and NIH research funding— proving that this technology is grounded in rigorous science, not just good intentions.

Teaching toward speech

InnerVoice isn't designed to replace natural communication. It's designed to teach it.

The Ultimate Goal

Speaking and typing—the rapid communication methods used by people throughout the world. InnerVoice leads toward these natural forms of expression.

Context-Based Learning

Language isn't retrieved by searching for individual words—it flows through neural pathways built by repeated use in context. InnerVoice builds those pathways.

Safe Practice Space

Practice communication in a safe, predictable virtual environment, then carry those skills into the physical world.

AI that identifies literally anything

Point your camera at any object—even unusual ones like a djembe drum—and InnerVoice will identify it, explain it, and start a conversation about it. Powered by modern large language models and optical character recognition.

Taking a photo of a djembe drum with InnerVoice

1. Point camera at any object

InnerVoice identifying the djembe and explaining it

2. AI identifies and explains it

Transform your visual world into language—connecting environment, speech, and text.

Practice real conversations

The AI chatbot teaches conversational skills naturally. Ask questions, make statements, practice speaking independently—all with an engaging animated avatar.

  • Natural back-and-forth exchanges that model real conversation
  • Explore topics of interest—from everyday objects to complex ideas
  • Build confidence in a safe, patient, non-judgmental environment
InnerVoice chat conversation practice

Avatars that capture attention

Create avatars from photos of yourself, family members, favorite characters, pets, or even drawings. The avatar serves as an engaging way to draw attention toward instructional material.

InnerVoice with girl avatar
InnerVoice with boy avatar

Touch the screen and the avatar's eyes follow your finger—teaching the foundational connection between pointing and eye gaze, which is how we assign meaning to words through jointly attending to items in the environment.

Social-emotional communication practice

Select emotions on the left side of the screen to change your avatar's facial expressions and tone of voice. Practice expressing feelings with embedded avatars or your own photos—learning the connection between emotions and how we communicate them.

Avatar showing happy expression

Happy

Avatar showing sad expression

Sad

Avatar showing frustrated expression

Frustrated

Understanding and expressing emotions is a key part of social communication. InnerVoice helps users see how facial expressions and tone of voice work together to convey feelings.

Basic Words vocabulary grid with word buttons

Standard vocabulary plus your own words

InnerVoice includes a research-based standard vocabulary with essential words like "I," "Want," "More," "Break," "Yes," and "You"—organized in a clear, easy-to-use grid.

  • Basic Words: Pre-loaded vocabulary for immediate communication
  • Video Stories: Social narratives and visual supports
  • My Words: Create custom buttons with photos, videos, or GIFs
  • Simple Editing: Add new words in seconds with our intuitive system

With embedded symbols, photos, videos, and GIFs, you can create a nearly infinite vocabulary tailored to the user's specific needs and interests.

Communication that comes alive

InnerVoice Mobile isn't just another AAC app. It's a complete communication and learning system built by speech-language pathologists who understand what actually works.

Animated Avatars

Create personalized avatars from any photo. Watch them speak with lip-sync animation and express emotions through facial expressions and tone of voice.

Vision to Speech

Point your camera at anything. Our AI instantly identifies objects and describes scenes, transforming the visual world into spoken language and text.

Video Self-Modeling

Import photos and videos to teach concepts, read social stories, learn communication skills, and shape echolalia into functional responses.

Remote Prompting

Parents and therapists can send real-time prompts that model communication within conversations, letting learners see themselves succeed.

Eye-Gaze Tracking

The avatar's eyes follow finger movements across the screen, teaching the foundational connection between pointing, eye gaze, and word meaning.

AI Conversation Practice

Practice natural conversations with our intelligent chatbot. Ask questions, make statements, and build speaking confidence independently.

Beyond static symbols

Many words need movement, context, or real-world examples to convey meaning. InnerVoice goes far beyond traditional picture boards.

Photos & Symbols

Use real photos, traditional symbols, or any image

Videos & GIFs

Show actions, movements, and abstract concepts

Visual Stories

Multi-sensory comprehension with speech and text

Animated Avatars

Engaging characters that model speech

Simple, fair pricing

Start free, upgrade when you're ready. Special discounts during Autism Acceptance Month (April) and AAC Awareness Month (October).

Free

$0

Get started with core features

  • Basic avatar creation
  • Core AAC buttons
  • Limited vocabulary
  • Text-to-speech
Download Free
Most Flexible

AI Toolkit

$4.99/month

Full AI-powered features

  • Everything in Free
  • AI Vision-to-Speech
  • AI Conversation Practice
  • Unlimited vocabulary
  • Video self-modeling
  • Remote prompting
Subscribe Monthly

Lifetime Access

$99.99one-time

Until January 1, 2026

Best value—pay once, use forever

  • Everything in AI Toolkit
  • One-time purchase
  • No recurring fees
  • All future updates included
Get Lifetime Access

Starting Jan 2026: $99/year due to advanced AI features

Video Stories solve the pronoun problem

When adults read social stories using "I" and "me," children with echolalia often get confused—who is "I"? InnerVoice solves this by putting the child's own avatar in the story.

Watch: Video Stories in action

The Traditional Problem

When a therapist reads: "When I get in the car, I will put on my seatbelt..."

The child hears "I" referring to the adult. Children with echolalia often refer to themselves as "you" because that's what others call them—leading to circular communication patterns that are hard to unlearn.

The InnerVoice Solution

The child's own avatar reads the story: "When I get in the car, I will put on my seatbelt..."

Now "I" clearly refers to the child. They see themselves saying "I" and "me" in proper context, building correct pronoun use through self-modeling.

Video Stories templates: Describe a Scenario, Narrate a Viewpoint, Outline an Instruction

Three templates plus "Make Your Own" for custom social stories

Pre-built stories for common scenarios

Leaving the House

Practice the steps of getting ready and leaving safely with a parent or caregiver

Crossing the Street

Learn to stop, look both ways, and cross safely—narrated in first person

Calling 911

Understand when and how to call for emergency help in a crisis situation

Build Your Own Social Stories

Create custom video stories using the child's own avatar. Embed GIFs, short videos, and images to help them understand any social scenario—from visiting the dentist to making friends at school.

  • Describe a Scenario:Show what will happen in a new or challenging situation
  • Narrate a Viewpoint:Explain thoughts, feelings, and perspectives in first person
  • Outline an Instruction:Break down multi-step tasks into clear, visual sequences

Why Self-Modeling Works

When children see themselves (via their avatar) successfully completing a task or navigating a social situation, they build confidence and understanding. This is based on Carol Gray's Social Stories framework, enhanced with video and personalized avatars.

"Sometimes my parents take me for rides in the car. It makes my parents happy when I wait for them to open the door. When I get in the car, I will put on my seatbelt."

— Example car safety story narrated by the child's avatar

Simple editing system—no training required

Create custom buttons in seconds. Add images, GIFs, or videos to teach context-dependent and abstract concepts like prepositions, pronouns, and core vocabulary words.

Long tap menu showing Folder and Button options for editing

Long tap to edit, delete, or move

Picture options menu with Camera, Gallery, Symbols, and GIPHY

Multiple image sources

Built-in GIPHY search for animated, context-rich buttons

Create Buttons Your Way

  • Camera: Take photos of real objects in the child's environment
  • Gallery: Use existing photos from your device
  • Symbols: Access standard AAC symbol sets
  • GIPHY: Search animated GIFs to show words in action

Flexible Speech Options

Auto-generated text-to-speech works instantly, or record your own voice for a personal touch.

Add button form showing hi button with Record and Playback options

Research-Based Color Coding

Buttons are automatically color-coded by word type using the Goossens', Crain, & Elder (1992) system—the same framework used by speech-language pathologists worldwide.

Nouns/Pronouns
Describing Words
Verbs
Location Words
Miscellaneous
Full vocabulary grid showing color-coded word buttons by category
App settings screen with Mode, Auto Speak, Auto Erase, and Grid adjustment

Adjustable Settings

Recorded or TTS mode, auto-speak, adjustable grid size

Custom vocabulary page with folders for Drink, Go, Feelings, and more

Organized Folders

Group vocabulary into categories like Drink, Feelings, Free Time

Avatar screen with custom vocabulary folders visible below

Integrated Experience

Avatar and vocabulary work together seamlessly

Powerful features for real learning

Translation Support

Download translation keyboards to communicate with people from diverse backgrounds

Handwriting Recognition

See your handwriting spoken by an avatar, connecting writing, reading, and speech

Quick Customization

Create or edit buttons in seconds with our intuitive, research-based interface

Emotion Pairing

Combine facial expressions, tone of voice, and text for richer communication

Evidence-Based Practices

InnerVoice incorporates multiple evidence-based practices recognized by the National Professional Development Center on Autism:

  • Technology-Aided Instruction (TAII)
  • Naturalistic Intervention
  • Parent-Mediated Instruction
  • Video Modeling/Self-Modeling
  • Visual Supports
  • Social Stories
  • Joint Attention Intervention
For Schools & Clinics

InnerVoice for Education

FERPA-compliant version built for classrooms, clinics, and protected settings. All the same powerful features with additional privacy protections.

  • Sharing features locked for student privacy
  • Easy data deletion via settings
  • Updated privacy policies for compliance
Get Education Version
Privacy First

Your Data Stays Yours

InnerVoice is built with privacy at its core. We process inputs through AI and return responses—we don't store your data.

No Data Storage

Images and text processed by AI are not stored on our servers. Process and forget.

Encrypted Transit

TLS 1.3 encryption for all data transmission—bank-level security.

FERPA Compliant

Education version meets federal student privacy requirements.

COPPA Compliant

Safe for children under 13 with proper privacy protections.

Microsoft AI for Good

“All you have to do is open a little crack in the door, and they all run through it.”

See how InnerVoice helped Sarah find her voice in the classroom.

“Ever since Sarah came into my classroom, she's not communicated with me or the other kids in any way. I needed a new way to reach her.”

Babies learn to communicate by looking directly at their parent's face, then learning to imitate. But babies with autism have big challenges looking at faces.

Digital faces engage them immediately.

Using Microsoft AI, InnerVoice creates animated avatars that simulate how parents naturally teach their children to talk. A child takes a picture, and an avatar describes it—just like mom or dad would.

The result?

“When InnerVoice came into the classroom, we noticed instant change. Sarah absolutely floored me. With InnerVoice, she has a voice.
Unlimited practice without judgment
Natural language modeling
Accessible to every child

Microsoft's AI for Good provided crucial technology that allows people to practice speech and language skills in a natural way. It gives every single person access.

Ready to bridge the gap between virtual and real?

Join 25,000+ families using InnerVoice Mobile to teach communication in context. Free tier available on iOS.