Use Your Own Audio for AI Avatar Videos

GoodAvatar accepts your own MP3 or WAV voice track. You can also generate a voiceover from a script with the built-in text-to-speech helper. Either way, the audio becomes the voice track for the talking avatar video.

Using your own audio is the right choice when you already have a recorded voice, a podcast segment, a course narration, or a song you have the rights to use.

Upload your own track

1. Prepare an MP3 or WAV file.
2. Keep the track within the current 120-second single-track limit.
3. Upload it in the create flow.
4. Add a portrait, review the credit estimate, and submit.

The video is generated in one pass from the complete track. You do not need to split the audio into sentences or merge video segments afterwards.

Generate a voiceover instead

If you do not have a recording, the create flow includes text-to-speech. Paste a short script, choose a voice, and generate the audio. The TTS helper is optional; video generation is the step that reserves video credits.

This is useful for:

• Product explainers with a written script
• Course intros that need a consistent voice
• Sales follow-ups with a personalized first line
• Social clips built from a repeatable template

Audio quality matters more than length

A clean 20-second track usually produces a better result than a noisy 90-second track. Avoid loud background music, clipping, and long silences. If you are using music, make sure you have the rights to publish it with the video.

For portrait guidance, read one portrait, one video. For the full workflow, see the AI avatar video generator page.

Cost check

Video generation uses 5 credits per second. A 30-second track uses 150 credits, about $1.69 at the Starter pack rate. Uploading your own audio does not add a separate charge.

Create a video with the 100 starter credits and test a short track before generating a longer one.