Cancel
Save as New
by
Create realistic lipsync videos with custom voices. Just upload a video or image, choose a voice from Google, OpenAI or bring your own voice from Eleven Labs to generate amazing videos with the Gooey.AI Lipsync Maker.
Run
Examples
API
2y ago
Upload a video/image with one human face.Recommended - mp4 / mov / png / jpg
This generates audio for your video
⚠️
Output videos will be truncated to 250 frames for free users. Please upgrade to generate long videos.
SD, Low-res (~480p), Fast (Rudrabha/Wav2Lip)
HD, Hi-res (max 1080p), Slow (OpenTalker/SadTalker)
OpenAI
Google Text-to-Speech
Eleven Labs
Uberduck.ai
Bark (suno-ai)
Azure Text-to-Speech
GhanaNLP Text-To-Speech
MMS TTS (Meta)
Alloy
Shimmer
Coral
Nova (TTS only)
Echo
Ash
Onyx (TTS only)
Fable (TTS only)
Sage
⚙️ Settings
Adjust the detected face bounding box. Often leads to improved results. Recommended to give at least 10 padding for the chin region.
Head
Chin
Left Cheek
Right Cheek
tts-1
gpt-4o-mini-tts
tts-1-hd
The HD version has less static noise in most situations at the cost of higher latency. Read more about the OpenAI voices and models here.
Run cost = 81 credits (Lipsync cost + TTS cost)
With each run, you agree to Gooey.AI's terms & privacy policy.
Download
Regenerate
🐞 Debug
🙋🏽♀️ Need more help? Join our Discord
Gooey.AI's base AI workflow with built-in RAG, web search, voice understanding of 1000+ languages, code creation + execution, API connections & integrations to create your own WhatsApp, Web, FB and voice AI …
Input your text, pick a voice & a Text-to-Speech AI engine to create audio. Compare the best voice generators from Bark/Suno, …
AI Animation Generator — create smooth, cinematic AI animations from text prompts. Generate 2D motion videos with keyframed prompt changes, zoom and pan camera moves, consistent style, and 4K/UHD looks. Great …
Create realistic Lipsync animations from any audio file. Input a sample face gif/video + audio, choose your AI model and we will automatically generate a lipsync animation that matches your audio. Use with …