Turn a drawing, mascot or pet photo into a talking character

4 steps

1. Pick a portrait that works

   Expression 2 animates the whole frame with no face detector or cropping step, so it works for any character (Expression 2). Every other model needs a clear, real human face and refuses a character before anything is charged.

   Input	Use for	Limits
   Image	the face	under 10 MB; one clear figure, neutral expression, facing the camera, face unobstructed
   Voice	voice cloning	30 seconds or more of clean speech, one speaker, no music (MP3, WAV or M4A); the whole file is used
   Prompt	the personality	required when there is no image

   For an animal or character, use a well-lit, front-facing picture with the face filling the frame. Without a voice sample, a voice is generated to match the persona; without a prompt, a persona is generated from the image (Create your own avatar).

   Expected

   An image URL that opens in a browser without signing in, under 10 MB, plus a voice sample and a prompt if you have them.

   Done: step 1

2. Create the character

   Send the portrait with "model": "expression-2". You can also create one in the dashboard at bithuman.ai, which starts on Expression 2.

   curl -s -X POST https://api.bithuman.ai/v1/agent/generate \
     -H "api-secret: $BITHUMAN_API_SECRET" -H "Content-Type: application/json" \
     -d '{"model": "expression-2", "prompt": "You are a friendly fitness coach.", "image": "https://your-site.example/portrait.jpg"}'
   # → {"success": true, "agent_id": "A80HVD8577", "status": "processing"}

   Credits are reserved when you submit and refunded automatically if the creation fails. A completed creation is not refunded, so a second generate is a second charge (Agents API).

   Expected

   An agent_id, with status processing.

   Done: step 2

3. Wait until it is ready

   Poll until status is ready or failed:

   curl -s https://api.bithuman.ai/v1/agent/status/A80HVD8577 -H "api-secret: $BITHUMAN_API_SECRET"
   # → {"success": true, "data": {"status": "ready", "progress": 1.0, …}}

   Expected

   status is ready: after about 2 to 2.5 hours, or up to 4 for an Expression 2 identity that needs more training.

   Done: step 3

4. Talk to it

   Pick the place it appears:

   • Its agent page: open https://www.bithuman.ai/embed/<agent_id> in a browser, allow the microphone and talk to it.
   • Your website: one script tag adds it as a floating widget (Website widget). Keep Anonymous Share on in its sharing settings; its sessions bill your account.
   • Your app: download the avatar file and render it on the device with the Swift package or the Android SDK (Put an animated character in an iPhone app, Android).

   <script src="https://www.bithuman.ai/widgets/bithuman-gadget.js"></script>
   <script>
     BitHumanGadget.init({
       agentUrl: "https://bithuman.ai/A23WJF0199?deployment=gadget",
       position: "bottom-right",
       buttonText: "Talk to us",
     });
   </script>

   Replace A23WJF0199 (the wise-pup sample) with your agent code.

   Expected

   The character idles, listens and answers out loud with its lips in sync.

   Done: step 4

All steps done. Next: make it your own.