How to Use the Speech Therapy Space

Clinician Guide

What is Speech Therapy Space?

Speech Therapy Space is an AI-powered feature within the clinician platform that allows healthcare professionals to create personalized, immersive therapy environments and conduct interactive speech practice sessions using AI avatars. Clinicians can generate custom virtual environments tailored to therapeutic goals, and guide patients through real-time conversation and speech exercises with AI-driven avatars — all within an immersive VR setting.

How to create a Speech Therapy Environment

1. From the clinician's platform Homepage, select "Speech Therapy Space"

2. Click "Access" on the Speech Therapy Environments

   

3. Enter a description of the environment you want to create. Examples for speech therapy:
   • "A calm, quiet library with soft lighting and bookshelves"
   • "A friendly classroom with colorful chairs and a whiteboard"
   • "An outdoor café with gentle background noise"
4. Click "Generate environment"
5. Review the result. If needed, adjust the prompt and regenerate.

📝 Note: Environment generation may take some time.

Speech Therapy Space offers two ways to run a session:

• Contextual Speech Environments – Run an immersive VR environment without an avatar, ideal for exposure, relaxation, or context-based speech practice.
• Avatar-Based Speech Practice – Run a session with an AI avatar inside the virtual environment for interactive conversation and speech exercises.

Starting a VR Session

1. Under Contextual Speech Environments, click "Launch"
   
2. Choose your patient, complete the session details and click "Start Session" to begin
3. Select the generated environment matching your session goals and click "Start Session"
   
4. Click "Play" to start the session in the patient's headset. 
   Note: The environment will play only in the headset, not on the platform.
   
5. During the session, you can change the environment by selecting another one from the library and clicking "Send to device"
   

Avatar-Based Speech Practice

Avatar-Based Speech Practice is a feature that allows patients to practice verbal fluency, word retrieval, voice control, and conversation through real-time interaction with AI avatars inside the virtual environment.

1. Under Avatar-Based Speech Practice, click "Launch"
   
2. Set the device and settings
3. Choose the virtual environment. 
   To add more AI-generated environments, use the Speech Therapy Environment Generator as explained above.
   
4. Select the appearance of your AI avatar
5. Select what you would like to focus on in the practice
   • Note: At the bottom there is an option for custom practice where you can enter your own instructions for the avatar
6. When ready, click "Start Session"
   
7. From this point, the session operates the same as described in the Starting a VR Session section above (steps 4–5)

📝 Note: You can click "Start Practice" under Avatar-Based Speech Practice at the top in order to view the characters and prepare a custom one before the session.

Clinical tips for Speech Therapy

• Match the environment to the therapy goal → For fluency training, use calm and low-stimulation environments. For social communication, use realistic social settings (e.g., a café or classroom).
• Reduce distractions → Avoid overly complex or visually busy environments that may interfere with the patient's focus on speech tasks.
• Use the environment as a conversation starter → The virtual setting can serve as a prompt for spontaneous speech practice.

💡 Clinician note: Generated environments can be saved and reused across sessions. Access your saved environments at any time from the Speech Therapy Space.

When should clinicians adjust the environment?

• If the patient seems distracted or overwhelmed → Regenerate with a simpler, calmer scene.
• If the environment doesn't match the clinical context → Refine the text prompt and regenerate.
• If the visual style feels too artificial → Switch to "M3 Photoreal" for a more realistic result.