← All models
P Video 2 Pro Avatar
Turn a portrait and speech into a talking video with Pruna's p-video-2-pro-avatar. Upload audio or write a script, with 30 voices and 10 languages, up to 3 minutes long.
Example
Details
- Accepts
- text
Pricing
- Price
- 2.5 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | integer | Random seed for reproducible generation. |
| audio | string | Speech audio, up to 3 minutes; the video matches its length. Overrides voice_script. |
| imagerequired | string | Portrait of the person who speaks (first frame). Supports jpg, jpeg, png, webp. |
| voice | —enum: Zephyr (Female), Puck (Male), Charon (Male), Kore (Female), Fenrir (Male), Leda (Female)… | Gemini TTS voice for voice_script. |
| prompt | string | What the video should show. |
| resolution | stringenum: 480p, 768p | |
| voice_prompt | string | Delivery instructions for the TTS voice (tone, pacing, accent, emotion). Not spoken. |
| voice_script | string | Exact words to speak with Gemini TTS. Required when no audio is uploaded. |
| voice_language | —enum: English (US), English (UK), Spanish, French, German, Italian… | Language of voice_script. |
| prompt_upsampling | boolean | Let a vision model look at the image and append the scene's own motion (rain, lights, background, body movement) to your prompt. Your words stay unchanged and come first. |
| enable_safety_filter | boolean | Block content in the toggleable moderation categories. The always-on rules apply either way. |