AI Podcast Video Generator
Put a face to your audio. Upload one host photo and a podcast excerpt, and get a video of the host speaking it, ready for YouTube, Shorts or social.
Input: Host photo + podcast or narration clip · Output: MP4, 4–120 seconds
Sample: Stories & podcasts · Host photo + podcast excerpt. Generated with OmniHuman 2.
How it works
- Step 1
Upload a clear photo of your host, or generate a portrait from a text description.
- Step 2
Add your podcast clip, narration or audiobook excerpt (WAV or MP3), or type text and generate a voice.
- Step 3
Generate. The model animates the face, head and body to match the audio, and you download the MP4.
Why use it
A face for audio-only shows
Turn highlights into video clips without filming anyone or booking a studio.
Works with your own audio
Bring a real recording, or write a script and generate a voice from text.
Consistent host
Use the same photo for every clip so your show keeps one recognisable look.
Short, shareable clips
Ideal for episode teasers and quotes. Each video is 4 to 120 seconds long.
Example direction prompts
Optional text you can add in the studio to guide the scene, movement and camera.
- “Calm podcast host in a warm studio, relaxed posture, small hand gestures, looking at the camera.”
- “Storyteller by a window at dusk, slow expressive gestures, soft nodding between sentences.”
- “Interview-style host leaning slightly forward, thoughtful pauses, natural eye contact.”
- “Audiobook narrator reading in a cosy library, gentle head movements, warm expression.”
Frequently asked questions
Can I turn a podcast episode into a video?
You can turn excerpts into video. Each generated video runs 4 to 120 seconds, so pick highlights, intros or key quotes and create several clips.
Do I need to record a new voice?
No. Upload your existing audio (WAV or MP3), or type a script and generate a voice from text for 1 credit per 100 characters.
Does it support more than one speaker?
A video is built from one photo and one audio track. You can create separate clips per speaker and combine them in your video editor.
What audio quality works best?
Clean speech without heavy background noise or music gives the best lip movement and expression.
Can I use my brand's host photo?
Yes, if you own the rights to the image or have the person's consent. Impersonating real people without consent is prohibited by our Acceptable Use Policy.
Make your first video
Plans start at $9.99/month. 1 credit = 1 second of video, and failed generations are refunded.