Upload the final voice track and a portrait. VlogMe maps the real timing, pauses, and delivery onto a talking avatar.
Export the voice
Add a portrait
Direct the delivery
Render the video01Voice file in, presenter out
This woodworker speaks a nine-second track made with ElevenLabs v3 — the same kind of file you export from ElevenLabs. Hedra Avatar lip-syncs the portrait to it: pauses, emphasis and breaths all come from the audio, and the voice itself is never re-generated.
Hedra Avatar · 9:169:16
02Show, then explain
01Bring the voice
Export the final MP3, WAV or M4A from ElevenLabs, or create the voice in VlogMe’s Audio Studio. Files up to 50 MB work; with Hedra Avatar a video can run up to ten minutes and always matches the audio length.
02Pick the framing
One voice file can drive a 9:16 Short, a 1:1 feed post and a 16:9 lesson. Render the format each channel needs without touching the recording.
Second voice · 9:169:1603Any voice
We kept the woodworker’s portrait and swapped in a different ElevenLabs voice with a softer, calmer tone. The mouth, pauses and emphasis follow the new track — the audio drives everything.
Video StudioAI avatar generator
Every talking-avatar tool in one place03How it works
Finish pronunciation, pauses, and emphasis in ElevenLabs before uploading.
Use a portrait you own or are licensed to animate.
VlogMe maps the supplied voice track onto the avatar and creates the video.
Finished examples
An onboarding welcome, a pasta tip in Italian, a workshop invitation
Onboarding9:16
Italian9:16
Third voice9:16Complete AI video creation
Your approved voice stays exactly as recorded. Render it with a new presenter or format in Video Studio, make SRT captions from it in Audio Studio, trim and title the clip in Video Editor, and translate the finished video with DUB.
Questions before you create
No. ElevenLabs is an independent company and trademark. VlogMe’s Audio Studio uses ElevenLabs voices as a provider, and this workflow also accepts audio you export from your own ElevenLabs account.
No. The talking-avatar workflow follows the uploaded audio’s timing and sound.
Only when you have the speaker’s permission and comply with the voice provider’s terms and applicable law.
MP3, WAV or M4A up to 50 MB. Hedra Avatar accepts up to ten minutes of audio per video; OmniHuman 1.5 and HeyGen Avatar V up to 60 seconds.
Yes. Any clean speech recording works — another text-to-speech tool, a podcast mic or your phone.
Credits per second of your ElevenLabs track, at the rate of the avatar model you choose; uploading the voice you already have costs nothing. There is no free plan: buy credits when you are ready, and the studio shows the estimate before you render.
Your voice track is ready
Choose the voice track and the portrait here — no account needed yet. Sign in when you continue: both upload to Lab and open in Talking avatar, and you see the credit estimate before anything renders.
Credit estimate before generation · Buy credits only when you need them
