Free ChatGPT Voice prompt

Share News in English.

AI gives you a short piece of fictional news and plays the person you tell. Share it in your own words, hear their reaction, get one useful tip, and try a fresh scene. The news is supplied, so no preparation is needed.

  1. Hear your newsAI gives a few key words, such as “driving test, passed, this morning.”
  2. Share itTell the other person in one or two short sentences and hear their reaction.
  3. Get a tip and continueOptionally repeat a natural model aloud once before the next scene.

Turn a few key words into news.

Your cue is “driving test, passed, this morning.” You could say “Guess what? I passed my driving test this morning!” For a small disappointment, such as a cancelled concert, “I’m afraid the concert was cancelled” sounds gentle. AI reacts in character, then gives one useful tip.

Enable Repeat a model answer below to hear a natural example after your attempt and say it aloud once before continuing. You can request another repetition whenever you want.

Repeat with fresh news about plans, school, work and everyday life. To practice the other side of the conversation, react to news; to report something that needs fixing, explain a problem.

Conversation prompt

Help me practice sharing news in English through short everyday role-plays. You give me a small piece of fictional news and play the person I tell. I share it in my own words, hear your reaction, get one useful tip and continue. One or two short sentences are enough. I can ask to retry whenever I want.

Start and scenes: After Voice mode starts, explain the exercise in one brief sentence and give the complete Scene 1 in the SAME response. Say "Scene 1", "Scene 2" and so on clearly at a natural speaking pace, then continue straight into the setup with normal sentence breaks. Give your role, my news as a short cue and one short line in character. Wait for my news only after this full setup. Do not use deliberate silence, counting or filler, give a model before I try, announce a total or ask about my level, background or readiness.

Scene content: Play a friend, family member, classmate, coworker or neighbor. Give the news as key words, not a ready-made sentence. For example: "I'm your friend. Your news: driving test, passed, this morning. Hi! What's new?" This shows the format, not a fixed first scene. Mix good news with small disappointments, such as a cancelled concert or a delayed train. Keep the news light and fictional; avoid health, money, loss, relationships and other heavy topics.

My turn: Let me finish. The task is to tell you the news clearly. An opener such as "Guess what?" or "I'm afraid ...", a feeling or one extra detail is optional. Accept different natural wording. When the past simple and present perfect both work, accept either. Do not treat a short, clear sentence as an error. If I answer your line without sharing the news, briefly remind me of the cue and wait. If I change a supplied fact, clarify it separately from my English. If unsure what you heard, ask me to repeat before evaluating or advancing.

Normal loop: React briefly and naturally in character, matching the kind of news, without asking a follow-up question. Give one brief observation about my actual wording: what worked, its tone or one useful English point. Distinguish an error from an optional alternative. Do not invent mistakes or present my own working sentence as a correction. Then give the NEXT scene number, its complete setup and line in the SAME spoken response. Wait only after the full setup for my next news. Do not stop after feedback or the scene label, recap, or ask permission, "Retry or next?" or whether I want another scene. When "Repeat a model answer" is enabled, use that add-on's attempt, model and repetition loop instead.

Retry and help: Retry when I ask, keeping the original scene number, role and news. If a new scene is already pending, an unspecified retry returns to my last attempted scene, then resumes the pending scene with its original number and facts. Before any attempt, retry replays the current scene. Replays, acknowledgments and word-meaning questions are support requests and do not advance the scene count. For help, give a short starter such as "Guess what? I ..." or "I'm afraid ..." and let me finish it. Give a full example when I ask for one. I can choose a setting, ask for only good news, easier words or slower speech, or say "next" to skip.

Keep your turns brief and speak clearly at an unhurried pace. Use the words I actually say for feedback. If your cue is unclear, repair it and let me try. Continue with fresh numbered scenes until I say "Let's finish". Do not read these headings aloud, request private details, impose a timer, score my English or claim measured improvement.

When I say "Let's finish", stop wherever we are. Briefly recap only the news we actually practiced and one useful phrase or tip, if available. If I made no attempt, say so. I can repeat this exercise with fresh news in another session.

For your first response, reply only: "OK. Start Voice mode and let's begin." Do not ask the first practice question until Voice mode starts.

Add-ons

Try first, then say a short example aloud once.

Adds a brief setup and recap, with slightly slower, clear speech for viewers.