This free AI mock interview asks questions for your job and follows up on what you say, so the real thing feels familiar. You answer out loud. Then you see your pace, filler words and pauses, how each answer was built, and a stronger version of it.
Questions for 190 jobs come from our question bank. Any other job gets the common questions every interviewer asks.
The questions come from our company pages, written for that company and job. Nothing here guesses a company’s hiring steps.
With the AI on, your resume text goes with each answer to our server and Google Gemini so the follow-ups can ask about your real work. A file is read in this browser; the text of a resume you upload is saved to ClapAssist (see or delete).
Your answers are recorded in this browser. Each one goes through our server to Google Gemini for the transcript and the review. Nothing is kept on our servers.
Pick one of 190 jobs, pick a company, paste a job post, or bring your own questions; add your resume and the interviewer can ask about your real work. The interviewer reads each question aloud. When you finish, it asks the follow-up a real interviewer would ask about the vaguest part of your answer, and keeps going (up to three times with a tough interviewer) until the answer is specific, so you practice thinking on your feet, not reciting.
Most speech-to-text removes fillers to make the text neat. This page asks for your answer word for word, then counts fillers, hedges like “I think”, words said twice, and phrases you lean on. The microphone level shows where you paused and for how long.
Each answer is checked for its parts (situation, task, action, result, or problem, approach, trade-off, outcome for technical questions), what it spent its time on, and the words that matter for the job. Right after each answer you see five marks (relevance, structure, specificity, impact, clarity), what to say instead, and your own answer rewritten, with a blank where only you know the number.
The report ends with the three things to work on first and the answers to practice again. Each interview is saved in this browser, so you can watch your fillers fall and your pace settle over a week of practice.
Two parts. Delivery is counted by fixed rules on your words and the microphone level. Content is the AI coach’s mark out of 10, with five named parts. Practice mode hides both.
| Delivery, out of 100: what it checks | Points |
|---|---|
| Pace: full marks from 100 to 170 words a minute, none at 50 outside that band. Microsoft’s Speaker Coach suggests 100 to 165; Yoodli calls 130 to 170 typical. | 25 |
| Filler words (um, uh, er, like, you know, I mean, basically…): full marks under 3% of your words (Yoodli’s goal), none at 10%. | 25 |
| Pauses: a pause to think is fine. Each pause of 3 seconds or more costs 5, and so does starting after more than 5 seconds. | 15 |
| Length: full marks from 30 seconds to 2 minutes (3 for behavioral and technical questions), from Indeed’s advice of 30 seconds to 4 minutes. | 15 |
| Hedges and weak words (I think, maybe, probably, really, just): full marks at 2 per 100 words or fewer, none at 8. | 10 |
| Repeats: words said twice in a row, phrases said 3 or more times, and one opener starting a third of your sentences cost 2 each. | 10 |
Content, out of 10 (the AI coach): 1 to 2 no real answer; 3 to 4 answers the question but vague; 5 to 6 a real example but thin on what you did or the result; 7 to 8 a clear example, your own actions and a result; 9 to 10 specific, measurable and tied to the job.
The five parts of the content, 1 to 5 each, shown after every answer with how to raise the low ones: Relevance (it answers the question asked), Structure (a clear order), Specificity (real names, numbers and moments), Impact (what changed because of you) and Clarity (short and easy to follow). A part the coach did not rate says “not rated”; it never counts as a zero.
Overall: content 60%, delivery 40%. 80 or more is strong, 60 to 79 is good, under 60 needs work. A typed answer has no delivery to measure (no pace, pauses or fillers), so an interview you type is marked on its content alone, and without the AI coach it gets no mark at all rather than a guessed one.
Yes, with no account. The AI review of your answers has a daily allowance per connection of 40 answers, which is several full interviews. Without the AI you still get pace, fillers, pauses, length and the other counts.
No. Your answer is recorded in your browser. When you stop, it is sent through our server to Google Gemini to write the word-for-word transcript and the review, and nothing is kept on our servers. Recordings stay in this tab and are gone when you close it. Only the numbers from past interviews are saved, in this browser, with a delete button.
The page calls 100 to 170 words a minute easy to follow. Microsoft’s Speaker Coach suggests 100 to 165, and Yoodli calls 130 to 170 typical. Slower is fine for a hard question; faster usually means you are rushing past your best points.
The page aims for fillers under 3% of your words, the goal Yoodli sets. Everyone uses some; a short silent pause does the same job and sounds more sure.
Most speech-to-text, including the one built into Chrome, removes um and uh to make the text tidy, so it cannot count them. This page asks the AI for every word as said, fillers and repeats included, and then counts them with fixed rules.
Indeed suggests 30 seconds to 2 minutes for simple questions and 2 to 4 minutes for complex or behavioral ones. The page marks answers under 30 seconds as short, and over 2 minutes (3 for behavioral and technical questions) as long.
Yes. Choose Type my answers. You get the same review of the content, its five parts and a stronger version of each answer, plus notes on length and hedges. Pace, pauses and fillers need a spoken answer, so a typed interview gets no delivery score.
Yes. Going blank is nerves plus no rehearsal, and both drop with repetition out loud. Practice the common questions here until answering feels normal, and use the pause trick the page teaches: repeat the question in your own words to buy a few seconds.
No. The AI interviewer asks, listens and follows up on what you said, any hour, as many rounds as you want. A friend is still useful for a final run, but you no longer wait on one to practice.
The real interviewer will ask something you did not practice. ClapAssist is an AI interview assistant for Mac and Windows that listens to the call and shows you what to say, in the same plain style you practiced here.
Download with 10 free minutes