Free ChatGPT Voice prompt
Give Directions in English.
AI gives you a short fictional route and plays a visitor, guest or new coworker who asks the way. Explain it in your own words, hear them repeat what they understood, get one useful tip, and try a fresh scene. The route is supplied, so no preparation or local knowledge is needed.
No Leleka Speak account is needed for the direct option. Open the conversation, then start Voice mode. This is informal speaking practice. AI feedback and speech interpretation can be mistaken.
- Hear the routeAI gives a few key words, such as “straight ahead, left at the bank, pharmacy on the right.”
- Give directionsExplain the way in one or two short sentences and hear the visitor repeat what they understood.
- Get a tip and continueOptionally repeat a natural model aloud once before the next scene.
Turn key words into directions.
Your cue is “straight ahead, left at the bank, pharmacy on the right.” You could say “Go straight ahead, turn left at the bank, and the pharmacy is on your right.” A shorter “Straight on, left at the bank, and it's on your right” also works. The visitor repeats back only what you said, so a missing turn or a mix-up between left and right is easy to notice. Then AI 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 routes in a town, a station, a mall, a school, an office or a hotel. To ask the way yourself, ask for help; to explain how to do a task, give simple instructions.
Conversation prompt
Help me practice giving directions in English through short everyday role-plays. You give me a short fictional route and play someone who asks me the way. I explain it in my own words, hear you repeat it, 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 and where we are, the route as a short cue and one short question in character. Wait for my directions 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 visitor, guest or new coworker asking the way to a nearby place in a town, station, mall, school, office or hotel. Give the route as key words, not a sentence: two or three parts, such as a turn at a landmark and which side the place is on. For example: "I'm a visitor outside the train station. The route: straight ahead, left at the bank, pharmacy on the right. Excuse me, how do I get to the pharmacy?" This shows the format, not a fixed first scene. Use familiar words, such as stairs or traffic lights. Keep places fictional, without real addresses, driving or emergencies. My turn: Let me finish. The task is to give the whole route in order; "Sure" is optional. Accept different natural forms, such as "Go straight ahead", "Turn left at ..." or "It's on your right." Imperatives are polite in directions. If I answer your question without giving directions, briefly remind me of the cue and wait. If I leave out a part, change the order or mix up left and right, name it in your feedback, separately from my English, and continue in the same response. An extra detail that keeps the same route is fine. If unsure what you heard, ask me to repeat before evaluating or advancing. Normal loop: Reply briefly in character, repeating back only the route I actually gave, such as "OK, straight ahead, left at the bank, and it's on my right. Thanks!" Do not fix a missing or changed part or ask another question. Give one brief observation about my actual wording: what worked, its clarity 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 question in the SAME spoken response. Wait only after the full setup for my next directions. 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, place and route. 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 "Go straight ..." and let me finish it. Give a full example when I ask for one. I can choose a place, ask for an easier route 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. In one or two sentences, recap what we actually practiced without listing every scene, plus one useful phrase or tip, if available. If I made no attempt, say so. I can repeat this exercise with fresh routes 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.