The Roleplay and Results views are the core of a Roleplay Session. The two views belong to the same AI Roleplay activity. The Roleplay view defines the conversation your learner practices. The Results view closes the loop with an automated score and coaching summary. This article explains each configuration option and how to use it to build a Roleplay Session that meets your training goal.
Configure the Roleplay View
To configure the Roleplay view:
Add an AI Roleplay activity to your video, and then select the Roleplay view.
Choose your Activity Type: Cold call, Field sales, Manager feedback, Customer conversation, Discovery call, or Custom.
Fill in each field described in the sections below.
Who Opens the Call
Who opens the call sets whether the Avatar or the learner speaks first. You can set this on any activity type.
Select the Roleplay view.
Under Who opens the call, choose the Avatar or the learner.
During a Roleplay, the Avatar responds to what the learner says. The Avatar pushes back, concedes points, asks follow-up questions, and refers to what the learner said earlier.
Persona
The persona is the person your learner speaks to. Choose or define a persona that matches the scenario, such as a customer, prospect, manager, teammate, or direct report.
Define these fields:
Name: The persona's name.
Base personality: The persona's demeanor.
Job title: The persona's role.
Company: Where the persona works.
Background: Stable facts about who the persona is that hold true in any conversation.
Personalization: Let learners tailor the Roleplay to their own context before they start speaking with the Avatar.
To turn on personalization:
Set up a default scenario, persona, and scoring for the activity.
Turn on Personalization in the Roleplay view.
When a learner reaches the Roleplay, the coach asks the learner a few questions about their context. The learner describes as much or as little detail as they like. Personalization adjusts the persona's job, background, and personality, and parts of the scenario, such as the call context and objections. Learners cannot change the success criteria or the persona's name and appearance. Scoring stays the same whether or not a learner personalizes, and learners can skip personalization to use the default persona.
Think of Background as the persona's character sheet, which describes who the persona is before this specific situation. The more grounded and specific the background is, the more realistic the conversation feels. Background can include how long the persona has been in their role, how the persona feels about feedback or conflict, and relevant personal context the persona carries into the conversation.
✍️ Keep the situation out of Background. What is happening right now belongs in Instructions, not Background. If you use AI to draft the persona, check each sentence afterward. If a sentence describes what is happening right now, move the sentence to Instructions.
Avatar and Background
The Avatar and background set how the persona looks during the Roleplay.
In the Avatar picker, select the Interactive tab.
Choose an Avatar. The Interactive tab includes all Express-3 stock Avatars and most Express-2 stock Avatars.
Select a background. Synthesia combines the Avatar and background into a webcam-style frame.
Generating the webcam frame can take up to 30 seconds.
(Optional) Select Customise Avatars to change the Avatar's outfit and space with a text prompt, or start from a preset.
✍️ These options apply to new Roleplays. Existing Roleplays are not affected.
Voice and Language
The voice you choose sets the language for the whole Roleplay. The Avatar, the coach, and the written feedback all use the language of the Roleplay.
Roleplays are available in English, Spanish, German, French, Chinese (Mandarin), Italian, Polish, Portuguese (Portugal), Portuguese (Brazil), Arabic, Hindi, Dutch, Swedish, and Turkish.
English Roleplays can use a US, UK, or Australian English accent. Set the accent separately for the Roleplay Avatar and the coach.
Instructions
Instructions describe the specific situation the learner walks into, which is what is happening right now in this conversation. The AI uses Instructions to stay in character. The learner does not see this text, so the learner works out the situation through the conversation itself.
Write 3–5 sentences, as if you are briefing an actor before they go on stage. Include:
What prompted the conversation
What the persona knows
What the persona does not know
How the persona feels at the start
Any conditional behavior you want the AI to follow
For example:
You are a prospect who requested a demo after researching Synthesia. You are interested, but you are worried about cost and whether your team will actually use the product. You have 20 minutes before your next meeting, so you want clear answers quickly. If the learner asks thoughtful discovery questions, share more detail about your team's training goals.
💡 Instructions have the biggest impact on Roleplay quality. If the conversation is not going the way you want, adjust this field first.
Objections
Objections are the pushbacks and challenges the persona raises during the conversation. Objections create the friction that makes the learner use the skill. Write 3–5 objections from the persona's point of view, grounded in the scenario.
The AI weaves these objections into the conversation naturally. The AI does not read the objections word for word, but the objections guide how the persona responds.
✍️ Write the objections, not the answers. Include only what the persona says, not how the learner should respond. The learner's job is to work out the response.
Examples for a sales Roleplay
Examples for a sales Roleplay
"We're not budgeted for this this year."
"Your competitor's pricing is lower."
"We need to get buy-in from our CFO first."
Examples for a customer support Roleplay
Examples for a customer support Roleplay
"This is the second time this has happened to me."
"I don't have time for a long process to fix this."
"I want a refund, not a replacement."
Examples for a manager feedback Roleplay
Examples for a manager feedback Roleplay
"I don't understand why I got a lower rating than my peer."
"I'm not sure this feedback is actionable."
"I feel like this is the first time I'm hearing about this."
Skills
Skills are the observable behaviors the AI scores the learner on after the Roleplay. Skills drive the feedback scene, which decides what the learner gets credit for, what the coaching highlights, and whether the learner passes, if you use pass/fail.
Where Skills Live
Skills are organized under two tabs:
Synthesia: A library of prebuilt skills that Synthesia maintains, ready to add to any persona.
Workspace: Custom skills that your team creates.
To create your own skill, select + New skill, and then define a skill specific to your team's methodology. The skill appears under the Workspace tab.
You can also ask Assistant to change the skills of a Roleplay instead of editing the Skills panel directly. Describe what you want, and Assistant reads the current skills, asks which skills you want to use instead, and reuses a matching skill from your workspace library where one exists.
Write Effective Skills
How many: Add 3–5 skills. More than 5 skills dilutes the signal and makes feedback harder to act on.
Weighting: Each skill carries a weight, and the weights add up to 100%. To stop a weight from redistributing when you adjust other weights, select the lock next to that skill.
What makes a good skill: Write skills as observable behaviors you could watch happen in a conversation, not abstract qualities. The AI scores based on whether the behavior shows up, so vague skills produce inconsistent scoring. For example, use "Acknowledges the employee's perspective before introducing their own point of view" instead of "Shows empathy".
The rubric: Each skill has a rubric, which describes what each score level looks like. The AI uses the rubric to evaluate the conversation. Write rubric criteria in terms of what the learner did or did not do, not how the learner felt or what the learner intended. Each rubric level is split into three sub-levels. A learner who shows part of the next level up moves up one sub-level, so scores show progress within a level.
Examples of abstract and observable skills:
❌ Too abstract | ✅ Observable |
Shows empathy | Acknowledges the employee's perspective before introducing their own point of view |
Communicates clearly | Uses specific examples rather than general statements when describing the issue |
Stays calm | Doesn't interrupt or escalate when the employee pushes back |
✍️ The rubric field is for the AI's evaluation criteria, not learner-facing feedback copy. Think of the rubric as instructions to the scorer, not a message to the learner.
💡 If you create skills from scratch, use AI to draft them. Give the AI your scenario context and ask it to write 4 observable skills with a 0–3 rubric for each. Then review and adjust the skills. This is much faster than starting from a blank field.
Time Limit
The time limit sets the maximum conversation length. When the learner reaches the limit, the Roleplay scene ends and the learner moves to the feedback scene.
Recommended ranges are:
5–7 minutes for practice
8–12 minutes for assessments
If a learner finishes before time runs out, the learner can end the call early. If the learner reaches the time limit, the Roleplay scene ends automatically. Either way, Synthesia scores the learner on the conversation they had.
💡 Tell learners the time limit in your scripted intro scene. Knowing there is a limit changes how learners pace the conversation.
Configure the Results View
The Results view is auto-generated. You set the logic, and the AI writes the feedback.
To configure the Results view:
Select the Results view on your AI Roleplay activity.
Set the passing score, for example 75%, or turn pass/fail off.
When pass/fail is off, learners still get their score, skill scores, and coaching feedback, without a pass or fail result.
Turn Retries on or off, depending on whether the Roleplay is practice or an assessment.
✍️ If you change the pass/fail setting, Synthesia does not rescore past attempts.
What's Next?
📚 To build a full Session step by step, check out How do I create a Roleplay Session?
📚 To build one alongside a guide, take the Build your first Roleplay Session course in Synthesia Academy.
📚 For a full reference, visit Roleplay Sessions – Synthesia Docs.