AI Presenter Video: Turn One Photo and a Lesson Script into a Talking Presenter
VdoBloom’s Course Presenter is an AI presenter video maker. It turns one photo and a typed script into a waist-up talking presenter video. You type the lesson, pick one of 21 AI voices and upload a front-facing photo. VdoBloom records the voice-over, and the person in the photo presents it with natural head movement, gestures and steady eye contact. Nobody needs a camera or a microphone.
Is it free? The 10 free signup credits are not enough for a presenter video. Pricing is per second of speech plus the voice-over. On the Standard 720p model a 30-second lesson is about 101 credits, and a full minute is about 196. Credits start at 300 for $19.50 as a one-time pack that never expires, or $15 a month. The exact estimate shows on the Generate button as you type.
It is built for online course creators, coaches, L&D and HR teams, and anyone recording training, onboarding or explainer lessons. Standard and Pro videos run up to 5 minutes each. Longer scripts, up to 20,000 characters, are split into lesson videos at sentence ends automatically.
How it works
- 1
Confirm consent
Tick the consent box to confirm you have the right to use the photo. Use your own photo, or one of a person who has agreed to present.
- 2
Type or paste the lesson script
You can paste up to 20,000 characters, about a whole course module. If it is longer than one video takes, it is split at sentence ends into parts, and each part shows its estimated length.
- 3
Choose the framing
Choose At a desk (seated, waist-up), Plain studio (clean background, waist-up) or Keep my photo. The background comes from your photo, so upload a photo taken in the setting you want.
- 4
Pick a voice and quality
Choose one of 21 ElevenLabs voices and a quality: Standard 720p, Pro 1080p, or OmniHuman 1.5 for clips up to 60 seconds.
- 5
Upload the presenter photo
Use a clear, front-facing, waist-up photo with even light on the face.
- 6
Generate each part
The voice-over is recorded first, then the video renders, usually in three to six minutes. For a split script, the tool moves to the next part after each one starts.
Why use this tool
Type it, don’t record it
Your script is voiced by a natural ElevenLabs voice, so you need no microphone, recording booth or retakes.
One photo, one presenter
Any clear front-facing photo becomes the presenter, framed waist-up and speaking to the viewer.
Up to 5 minutes per video
Standard and Pro run up to 300 seconds per video. OmniHuman 1.5 runs up to 60 seconds.
Long scripts split into lessons
Paste a whole module, up to 20,000 characters, and it is split at sentence ends into lesson-length videos.
One charge, full refund on failure
The voice and the video are billed together on one job. If any step fails, both are refunded. If the voice-over cannot be made, nothing is charged.
Live cost estimate
As you type, the server quotes the voice-over and the video for each part, and the price shows before you generate.
What is an AI presenter video?
An AI presenter video shows a person talking to camera and delivering a script, generated by AI instead of filmed. Many tools ask you to pick a stock avatar or record a training clip of yourself. VdoBloom’s Course Presenter starts from a single photo, so the presenter can be you, a colleague or a brand face who has agreed to appear.
The flow has two AI steps. A text-to-speech model voices your script, and a talking-avatar model animates the photo so the lips, head and hands move with that voice-over.
Which quality should I pick, and what does it cost?
Each video costs the voice-over (5 credits per 1,000 characters, rounded up) plus the video, priced per second of speech. The figures below use about 14 characters per spoken second. The final charge uses the measured length of the recorded voice.
| Quality | Max per video | Video rate | 30 s lesson | 60 s lesson |
|---|---|---|---|---|
| Standard 720p (Kling AI Avatar) | 5 min | 954 credits per 300 s | ≈ 101 | ≈ 196 |
| Pro 1080p (Kling AI Avatar Pro) | 5 min | 1,910 credits per 300 s | ≈ 196 | ≈ 387 |
| OmniHuman 1.5 | 60 s | 10.8 credits per second | ≈ 329 | ≈ 653 |
What does a full course cost?
Worked examples on Standard 720p, voice-over included. A Lite pack is 300 credits for $19.50, paid once, and the credits never expire.
| Content | Script length | Credits (approx.) |
|---|---|---|
| A 30-second welcome clip | ≈ 420 characters | 101 |
| A 1-minute lesson | ≈ 840 characters | 196 |
| A 2-minute lesson | ≈ 1,680 characters | 392 |
| A 5-minute lesson (one full video) | ≈ 4,200 characters | 979 |
How a long course script becomes lesson videos
One video on Standard or Pro holds about 4,200 characters of script, which is roughly five minutes of speech at the tool’s estimate of 14 characters per second. OmniHuman 1.5 holds about 840 characters, or 60 seconds. Paste a longer script and the tool splits it at sentence ends into numbered parts, each with its estimated length. If a sentence is too long, it splits at a space.
You generate the parts one at a time. After each part starts, the selector moves on to the next one, so you can work through a module in order. Each part is its own video in your Creations library, which makes it easy to redo a single lesson after you edit its script without paying to re-render the rest.
Use cases
Anywhere a talking head explains something better than slides alone.
- Online course lessons, module intros and recap videos.
- Employee onboarding, policy walkthroughs and compliance refreshers.
- Coaching and tutoring explainers you can update by retyping the script.
- Product and feature walkthrough intros for customer education.
- Welcome videos for communities, cohorts and membership sites.
Read more: AI training video generator guide · AI presenter video for online courses · AI training video tool comparison
Tips for a natural presenter
The photo and the script shape the result more than any setting.
- Use a waist-up photo, facing the camera, with soft even light and the face large in the frame.
- Take the photo in the setting you want. The framing option directs the delivery but keeps your photo’s background.
- Write for the ear: short sentences, one idea each, and contractions the way people actually speak.
- Split long modules into lessons of a minute or two. They are easier to watch, cheaper to redo and quicker to render.
- Spell out numbers, acronyms and brand names the way they should be said.
Limits to know
The presenter comes from one photo, with one presenter per video and a static camera. There is no stock-avatar library, slide or PowerPoint import, screen recording, burned-in captions or LMS/SCORM export. Assemble lessons with slides or captions in your course platform or video editor. The 21 voices are preset ElevenLabs voices; this tool does not clone your own voice. Videos are generated one part at a time.
Frequently asked questions
Can I make an AI presenter video from a photo?
Yes. Upload one clear, front-facing photo and type your script. The person in the photo presents it as a waist-up talking video with an AI voice-over. Only use photos you have the right to use.
Is the AI presenter video maker free?
Not on the free signup credits. A 30-second lesson on Standard 720p is about 101 credits, voice included. Credits start at 300 for $19.50, a one-time pack that never expires, and the price shows before you generate.
How long can a presenter video be?
Up to 5 minutes per video on Standard 720p and Pro 1080p, and up to 60 seconds on OmniHuman 1.5. You can paste up to 20,000 characters. Anything longer than one video is split into lesson parts at sentence ends.
Which voices are available?
Twenty-one ElevenLabs voices, including Rachel, Sarah, Charlotte, Alice, Matilda, George, Brian, Daniel, Liam and Callum. The voice-over is made with ElevenLabs Multilingual v2.
Can I use my own voice?
Not in this tool. It voices typed scripts with preset AI voices. To animate a photo with audio you recorded yourself, use the AI Avatar tool, which accepts an audio upload.
How much does a 1-minute presenter video cost?
About 196 credits on Standard 720p, 387 on Pro 1080p or 653 on OmniHuman 1.5, voice-over included. The final charge follows the measured length of the voice-over.
What photo works best?
A waist-up photo facing the camera, with even light on the face and the setting you want behind you. Avoid sunglasses, hard backlight, extreme angles and small, low-resolution crops.
What happens if a video fails?
The voice-over and video are one charge. If any step fails, both are refunded. If the voice-over itself cannot be created, nothing is charged.
Can I import slides or add captions?
No. The tool makes the talking-presenter video only. Add slides, captions or screen recordings in your course platform or a video editor.
Should I disclose that the presenter is AI?
Disclosure is increasingly expected, and some platforms and regions require it for synthetic people. Labelling the presenter as AI-generated is the safe default for courses and training.