> ## Documentation Index
> Fetch the complete documentation index at: https://docs.realtalkstudio.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Changelog

> New features, improvements and updates to Real Talk Studio

<Update label="Week of 31 July 2026" description="Session localisation for non-English roleplays" tags={["Localisation", "Session Review"]}>
  ## Full session localisation for non-English roleplays <Badge color="yellow">Localisation</Badge>

  When you run a simulation in a language other than English, the **live session**, **microphone check**, and **post-session feedback** now follow that language end to end, including score explanations, so learners stay in one language from start to finish.
</Update>

<Update label="Week of 10 July 2026" description="Studio feedback surveys and card reactions" tags={["Session Review", "Admin"]}>
  ## Studio feedback surveys <Badge color="blue">Admin</Badge>

  **Studio admins** can configure **end-of-session surveys** for their learners, with **rating**, **NPS**, and **free-text** questions. Responses appear in **session history**, **analytics**, and **CSV exports** so programme owners can measure usefulness and gather ideas for new scenarios.

  ## Feedback card reactions <Badge color="purple">Session Review</Badge>

  After a simulation, learners can tap **Agree** or **Disagree** on individual feedback cards so teams can see which coaching points landed. **Studio admins** see reaction summaries alongside survey results in reporting and exports.
</Update>

<Update label="Week of 3 July 2026" description="Customer Stories and moderation alerts" tags={["Website", "Admin"]}>
  ## Customer Stories <Badge color="blue">Website</Badge>

  The site now includes a **Customer Stories** section with video interviews and case studies from organisations using Real Talk Studio, so prospects and teams can hear how others practise difficult conversations before they sign up.

  ## Moderation flag email alerts <Badge color="blue">Admin</Badge>

  **Organisation super admins** now receive an email when post-session moderation flags learner messages, including the triggering content and a link to review the session, so compliance teams can act quickly without polling the admin hub.
</Update>

<Update label="Week of 26 June 2026" description="Korean localisation and session pause" tags={["Localisation", "Conversation Engine"]}>
  ## Korean language support <Badge color="yellow">Localisation</Badge>

  Real Talk Studio now supports **Korean** across the platform interface, roleplay creation, and practice flows, with matching **voice** options so Korean scenarios can run end to end.

  ## Pause and resume live sessions <Badge color="red">Conversation Engine</Badge>

  During **avatar** and **audio-only** simulations you can **pause** the session and pick up where you left off. The timer stops while paused, and live connections are torn down so you are not charged for idle time.
</Update>

<Update label="Week of 19 June 2026" description="Session warm-up and enterprise trust" tags={["Conversation Engine", "Website"]}>
  ## Session warm-up <Badge color="red">Conversation Engine</Badge>

  Before you begin a practice simulation you work through a short **warm-up**: preview how the conversation might open, consider a pivotal moment, choose a skill to focus on, and rate your confidence. The flow runs when you start practice (including demo sessions) so you enter the roleplay prepared rather than jumping straight to the microphone check.

  ## Enterprise trust centre <Badge color="blue">Website</Badge>

  New **Security**, **Trust Centre**, and **Responsible AI** pages give procurement and compliance teams a clear view of our ISO certifications, data practices, and how AI is governed in practice sessions. An on-brand certification banner highlights our ISO 27001, 9001, and 42001 credentials on the homepage.
</Update>

<Update label="Week of 18 June 2026" description="Enterprise trust and security" tags={["Website"]}>
  ## Enterprise trust and security hub <Badge color="blue">Website</Badge>

  New **Security**, **Trust Centre**, and **Responsible AI** pages give enterprise buyers one place to review **ISO 27001**, **ISO 9001**, and **ISO 42001** certifications, policies, and how AI is governed in practice sessions. The homepage highlights ISO certification for teams evaluating the platform.
</Update>

<Update label="Week of 12 June 2026" description="Polish localisation" tags={["Localisation"]}>
  ## Polish language support <Badge color="yellow">Localisation</Badge>

  Real Talk Studio now supports **Polish** end to end: the interface is available in **Polski**, and you can create and run **Polish** roleplays with speech recognition tuned for the language.
</Update>

<Update label="Week of 29 May 2026" description="Preparedness tracking and studio cohorts" tags={["Session Review", "Admin"]}>
  ## Preparedness confidence tracking <Badge color="purple">Session Review</Badge>

  Studios can enable **preparedness tracking** so learners rate how ready they would feel before a first attempt and again after the session, with repeat runs able to reference their previous score. **Studio admins** see before and after scores in session history, analytics, and CSV exports.

  ## Studio cohort management <Badge color="blue">Admin</Badge>

  **Studio admins** can create **cohorts**, assign members, and filter **session history** and **analytics** by cohort so reporting matches how programmes are organised.
</Update>

<Update label="Week of 22 May 2026" description="On-topic guardrails and harassment Take Action" tags={["Conversation Engine", "Session Review"]}>
  ## On-topic session guardrails <Badge color="red">Conversation Engine</Badge>

  Live **roleplay** sessions now keep practice focused on the scenario. If your messages drift too far off topic you see a **warning** in the transcript, and the session **ends** if off-topic turns continue, so time in the simulation stays aligned with the learning objective.

  ## Harassment Take Action flow <Badge color="purple">Session Review</Badge>

  After **harassment** practice simulations, learners complete a guided **Take Action** path before feedback: recognise what happened, choose who they would tell (line manager, HR, whistleblowing, or keep it private), and record their reflection, supporting compliance rehearsal without jumping straight to scores.
</Update>

<Update label="Week of 15 May 2026" description="Live session layout and guided AI creation" tags={["Conversation Engine", "Roleplay Builder"]}>
  ## Live session layout refresh <Badge color="red">Conversation Engine</Badge>

  During live simulations you get a clearer **progress** view (elapsed time and target duration), an **orientation strip** to open scenario context when you need it, and a **collapsible side panel** on larger screens. **Mood** is easier to read at a glance with a new **ring** indicator, **achievements** show locked and unlocked states more clearly, and **ending a session** now asks for confirmation so you are less likely to leave by mistake.

  ## Guided steps for AI roleplay creation <Badge color="red">Roleplay Builder</Badge>

  The **AI-assisted** roleplay builder now follows a clearer **step-by-step** flow, with dedicated screens for templates and authoring instead of juggling several panes at once, so you can move from idea to a ready-to-review scenario with less friction.
</Update>

<Update label="Week of 5 May 2026" description="Avatar cleanup and admin analytics" tags={["Avatars", "Platform", "Admin"]}>
  ## Interview and studio analytics <Badge color="blue">Admin</Badge>

  Organisation admins reviewing **interview** and **studio** sessions can see **persona** details and **non-verbal** presence alongside session history and CSV exports when that data was captured, supporting fuller coaching and compliance review.

  ## Legacy HeyGen and Simli removed <Badge color="green">Avatars</Badge>

  The application now supports **LemonSlice** and **LiveAvatar** only. HeyGen Streaming, Simli, and their npm packages have been removed. IT firewall guidance and environment variables were updated accordingly.
</Update>

<Update label="Week of 28 April 2026" description="Fast Track Default & Languages" tags={["Conversation Engine", "Localisation"]}>
  ## Fast track as default <Badge color="red">Conversation Engine</Badge>

  **Fast track** is now the **default** way into a simulation, aligned with current branding and styling. Session start includes the same **microphone and camera checks** as other flows where applicable, so setup stays predictable before you begin.

  ## Language expansion <Badge color="yellow">Localisation</Badge>

  The platform continues to broaden **language** coverage — including **French** in the interface set alongside existing locales, **additional locales** where relevant, and **expanded voice language** options so more scenarios match your learners' languages.
</Update>

<Update label="Week of 21 April 2026" description="Dark theme & feedback overhaul" tags={["Conversation Engine", "Session Review"]}>
  ## Dark mode for all sessions <Badge color="red">Conversation Engine</Badge>

  Sessions now use a single **dark theme** end to end — a deliberate **branding and UI refresh** so live simulations, completion, and shared feedback share the same look and feel instead of mixing light and dark surfaces.

  ## Feedback enhancements & overhaul <Badge color="purple">Session Review</Badge>

  Post-session **feedback** has been reworked: the completion flow is built around the **transcript**, with a clearer **tabbed** layout for reviewing outcomes. **Shared feedback** matches the new design system so learners and stakeholders see the same polished experience after a simulation.
</Update>

<Update label="Week of 14 April 2026" description="MCP Integrations" tags={["Documentation"]}>
  ## Model Context Protocol (MCP) <Badge color="blue">Documentation</Badge>

  **MCP** support lets teams and tools **create roleplays** from connected clients, with **documentation** and on-site copy explaining how Real Talk Studio **integrates** with MCP-compatible environments.
</Update>

<Update label="Week of 7 April 2026" description="Non-Verbal Roleplays" tags={["Conversation Engine"]}>
  ## Non-Verbal Roleplays <Badge color="red">Conversation Engine</Badge>

  Simulations can now run in **non-verbal** mode — practise reading cues and responding without relying on spoken dialogue, with clear messaging during camera and session setup where streaming behaviour differs from standard voice sessions.
</Update>

<Update label="Week of 24 March 2026" description="Realism Scoring" tags={["Session Review"]}>
  ## Conversation Realism Scoring <Badge color="purple">Session Review</Badge>

  Every simulation session now receives an automatic **realism score** — a measure of how closely the AI character's behaviour mirrors a real conversation. Admins can review scores across sessions to spot which scenarios are performing well and where prompts may need tuning.
</Update>

<Update label="Week of 17 March 2026" description="Homepage Refresh" tags={["Website"]}>
  ## Homepage & Practice Page Refresh <Badge color="blue">Website</Badge>

  The homepage and practice pages now feature preview videos and direct links to example simulations, so visitors can see the platform in action before signing up.
</Update>

<Update label="Week of 10 March 2026" description="Live Avatars & Widescreen" tags={["Avatars", "Roleplay Builder", "Voice"]}>
  ## LiveAvatar as primary streaming avatar <Badge color="green">Avatars</Badge>

  The platform uses **LiveAvatar** for realistic streaming avatars (via LiveKit). Legacy HeyGen Streaming and Simli integrations have been removed from the product codebase.

  ## Improved Avatar Appearance <Badge color="green">Avatars</Badge>

  Custom avatar image generation now produces more neutral, natural facial expressions and makes better use of screen space — characters look more lifelike and less artificial.

  ## Conversation Structure at Setup <Badge color="red">Roleplay Builder</Badge>

  Conversation flow is now generated when a roleplay is created rather than during the session, meaning faster starts and more consistent scenario delivery.

  ## EU Voice Processing <Badge color="orange">Voice</Badge>

  Voice processing is now pinned to European servers, reducing latency for UK and European users.
</Update>

<Update label="Week of 3 March 2026" description="Scenario & Session Improvements" tags={["Conversation Engine", "Roleplay Builder", "Session Review"]}>
  ## Scenario Info During Sessions <Badge color="red">Conversation Engine</Badge>

  A new toggle lets learners view scenario context and background information during a live session without breaking the conversation flow.

  ## Improved Emotional Range <Badge color="red">Conversation Engine</Badge>

  AI characters now express emotions with more subtlety and variation. The mood system has been refined to avoid rigid or predictable responses, producing more authentic conversational dynamics.

  ## Reordered Scoring Dashboard <Badge color="purple">Session Review</Badge>

  Realism scores now appear above transcript generation in the edit view, making it quicker to assess conversation quality at a glance.
</Update>

<Update label="Week of 24 February 2026" description="Custom Avatars & Voice Library" tags={["Avatars", "Voice", "Sharing"]}>
  ## Custom Avatar Creation <Badge color="green">Avatars</Badge>

  Create your own custom avatars for use in simulations — upload an image and generate a unique AI character that matches your organisation's scenarios.

  ## Expanded Voice Library <Badge color="orange">Voice</Badge>

  Browse and select from a full library of voices to find the right tone, accent, and personality for your characters.

  ## Custom Branded Share Links <Badge color="blue">Sharing</Badge>

  Shared simulation links now display your organisation's logo, reinforcing your brand when learners access sessions externally.
</Update>

<Update label="Week of 17 February 2026" description="Audit Readiness & Evidence" tags={["Website", "Conversation Engine"]}>
  ## Audit Readiness Interview Simulator <Badge color="red">Conversation Engine</Badge>

  A major new simulation mode designed specifically for audit preparation — practice responding to auditor questions in a realistic, pressure-tested environment.

  ## Audit Readiness Landing Page <Badge color="blue">Website</Badge>

  A dedicated landing page showcasing how Real Talk Studio helps organisations prepare for compliance audits through simulated interviews.

  ## Evidence Page <Badge color="purple">Session Review</Badge>

  A new Evidence page provides a centralised view of completed simulations and their outcomes, supporting compliance documentation and audit trails.
</Update>

<Update label="Week of 10 February 2026" description="Presentations & Interhuman Mode" tags={["Conversation Engine", "Session Review"]}>
  ## Presentation Mode <Badge color="red">Conversation Engine</Badge>

  A new simulation type for practising presentations and pitches. Deliver your content to an AI audience that responds with realistic questions and feedback. Includes moderation controls and post-session user feedback.

  ## Interhuman Mode for Presentations <Badge color="red">Conversation Engine</Badge>

  Interhuman mode — where a facilitator observes and guides the session — is now available for presentation simulations as well as standard roleplays.

  ## Transcripts in Admin <Badge color="purple">Session Review</Badge>

  Full session transcripts are now accessible directly from the site admin panel.
</Update>

<Update label="Week of 3 February 2026" description="Promo Videos & Pricing" tags={["Website"]}>
  ## Automated Promo Video Generation <Badge color="blue">Website</Badge>

  New tooling for generating promotional videos directly within the platform, replacing the previous static video assets with dynamic, up-to-date content.

  ## Pricing Page Refresh <Badge color="blue">Website</Badge>

  The pricing page has been redesigned with clearer tiers including a new free plan, making it easier for teams to evaluate Real Talk Studio before committing.

  ## Homepage Redesign <Badge color="blue">Website</Badge>

  A refreshed homepage with updated copy, new strategy positioning, and improved landing pages across the site.
</Update>

<Update label="Week of 27 January 2026" description="Translations & Persona Profiles" tags={["Localisation", "Roleplay Builder"]}>
  ## Multi-Language Support <Badge color="yellow">Localisation</Badge>

  Real Talk Studio is now available in **Spanish**, **German**, and **Czech**, with full translation across the platform interface.

  ## Persona Image & Description in Sessions <Badge color="red">Conversation Engine</Badge>

  The AI character's profile image and description now appear on the in-session screen, giving learners more context about who they're speaking with.

  ## Policy Adherence Scoring <Badge color="purple">Session Review</Badge>

  A new scoring dimension that measures how well the learner followed relevant policies during the simulation — available in session completion, roleplay setup, and review screens.

  ## Customer Persona Profile <Badge color="red">Roleplay Builder</Badge>

  A new pre-built persona type optimised for customer-facing scenarios, with an existing customer profile that adapts behaviour for service and sales simulations.
</Update>

<Update label="Week of 20 January 2026" description="Dynamic Personalities & Documentation" tags={["Conversation Engine", "Documentation"]}>
  ## Dynamic Personalities <Badge color="red">Conversation Engine</Badge>

  AI character personalities are no longer static — they now shift and respond dynamically during sessions, creating more authentic and unpredictable conversations.

  ## Platform Documentation <Badge color="blue">Documentation</Badge>

  Comprehensive product documentation is now available at [docs.realtalkstudio.com](https://docs.realtalkstudio.com), covering setup guides, network requirements, and platform capabilities.

  ## SSO Admin Improvements <Badge color="blue">Admin</Badge>

  Organisation admin controls for SSO have been streamlined, with team-level views and conditional visibility based on your SSO configuration.

  ## Connectivity Test <Badge color="blue">Admin</Badge>

  A new connectivity test tool helps IT teams verify that their network meets Real Talk Studio's requirements before rolling out to users.
</Update>

<Update label="Week of 13 January 2026" description="Speaking Feedback & Fast Mode" tags={["Session Review", "Conversation Engine"]}>
  ## Speaking Feedback <Badge color="purple">Session Review</Badge>

  Post-session reviews now include detailed feedback on the learner's speaking performance — pacing, clarity, and delivery alongside the existing content-based scoring.

  ## Fast Mode <Badge color="red">Conversation Engine</Badge>

  A new streamlined session start flow that gets learners into a simulation with near-instant setup — ideal for quick practice and repeat sessions.

  ## Assisted Turn-Taking <Badge color="red">Conversation Engine</Badge>

  A new "assisted mode" replaces manual turn-taking, automatically managing conversation flow so learners can focus on what they're saying rather than when to speak.

  ## Expanded Emotion System <Badge color="red">Conversation Engine</Badge>

  New emotional states including "busy" have been added to AI characters, broadening the range of realistic workplace behaviours they can exhibit.
</Update>

<Update label="Week of 6 January 2026" description="Audio-Only Mode & Cartesia" tags={["Conversation Engine", "Voice"]}>
  ## Audio-Only Mode <Badge color="red">Conversation Engine</Badge>

  A brand new way to run simulations — choose between avatar-based video sessions or audio-only mode at session start. Audio-only is ideal for phone-call simulations, lower-bandwidth environments, or when you want to focus purely on the conversation.

  ## Avatar or Audio Selection <Badge color="red">Conversation Engine</Badge>

  Learners can now choose their preferred session mode — avatar video or audio-only — when starting a simulation.

  ## New Text-to-Speech Engine <Badge color="orange">Voice</Badge>

  Cartesia has been added as a text-to-speech provider, delivering more natural-sounding voices with expanded language support and dynamic emotional expression.

  ## Persona Gender <Badge color="red">Roleplay Builder</Badge>

  Persona profiles now include gender, which is used to automatically select an appropriate voice when running audio-only sessions.

  ## Session Resilience <Badge color="red">Conversation Engine</Badge>

  Improved connection stability with WiFi status indicators, automatic session recovery on connection drops, and graceful handling of browser closures — your session progress is now saved even if you close the tab.
</Update>