# P-Video-2-Pro Avatar

`pruna/p-video-2-pro-avatar` · Pruna AI · video

Animate a portrait using a recorded voice or a written script. The model matches mouth movement and facial expression to the speech and supports videos up to three minutes.

[Model page](https://sociaro.com/models/pruna/p-video-2-pro-avatar) · [JSON](https://sociaro.com/models/pruna/p-video-2-pro-avatar.json) · [Model pricing](https://sociaro.com/pricing?model=pruna%2Fp-video-2-pro-avatar) · [Documentation](https://docs.sociaro.com/models/pruna-p-video-2-pro-avatar/) · [Playground](https://my.sociaro.com/playground/?model=pruna/p-video-2-pro-avatar) · [Launch page](https://sociaro.com/models/p-video-2-pro-avatar)

Video capabilities — `avatar-lip-sync`

## Use cases

- Turning a translated script into a presenter clip
- Animating a character portrait to an existing voice recording

## Technical details

- API model ID — pruna/p-video-2-pro-avatar
- Provider — Pruna AI
- Modality — Video
- Input — Text prompt · Images · Voice script · Audio
- Output — Video
- Endpoint — POST /v2/jobs
- Workflow — Avatar video
- Resolution — 480p · 768p

## Request parameters

- `image` (string, required) — Public https URL of the portrait: jpg, jpeg, png or webp, up to 20 MiB. It is the first frame and sets the aspect ratio.
- `audio` (string) — Public https URL of speech audio, 1 second to 3 minutes and up to 64 MiB. It sets the video's length and wins over voice_script. Send this or voice_script.
- `voice_script` (string) — The exact words to speak when no audio is sent. Send this or audio.
- `voice` (string) — Voice for voice_script: one of 30 named voices, each written with (Female) or (Male) after the name. Default Zephyr (Female).
- `voice_prompt` (string) — How the script is delivered: tone, pacing, accent, emotion. It is not spoken. Default "Say the following."
- `voice_language` (string) — Language of voice_script: English (US) (default), English (UK), Spanish, French, German, Italian, Portuguese (Brazil), Japanese, Korean or Hindi.
- `prompt` (string) — What the video should show. Default "The person is talking."
- `prompt_upsampling` (boolean) — Adds the scene's own motion, read from the portrait, after your words; false uses the prompt exactly as written. Default true.
- `resolution` (string) — Output resolution, each with its own per-second rate. Default 768p. The higher tiers, 1080p and above, are not offered yet.
  - Allowed values — `480p`, `768p`
- `seed` (integer) — Fixes the random draw: the same inputs and seed give the same result.
- `enable_safety_filter` (boolean) — Turns the generator's content check on or off. Default false.

## Pricing

Rates in USD. Catalogue timestamp 2026-11-21T02:23:44Z.

- USD 0.02 per second of output video · 480p · active
- USD 0.04 per second of output video · 768p · active

- Billed on the finished video, in whole seconds rounded down.
- Leaving out resolution gives 768p.

## Examples

### One API key

A studio presenter speaks the supplied ElevenLabs recording, listing four media types and explaining how to switch models.

[Result (video)](https://previews.sociaro.com/shared/promo/gallery/creative/pruna-recorded-presenter-1d4569f8.mp4) · [Poster](https://previews.sociaro.com/shared/promo/gallery/creative/pruna-recorded-presenter-7e2fad08.webp) · [Captions](https://sociaro.com/shared/promo/gallery/creative/pruna-recorded-presenter.en.vtt)

1152 × 768 · 24 fps

Source inputs

- [Recraft studio portrait (image)](https://previews.sociaro.com/shared/promo/gallery/alibaba-video/wan-studio-presenter-portrait.png) · [Thumbnail](https://previews.sociaro.com/shared/promo/gallery/alibaba-video/wan-studio-presenter-portrait-thumb.webp)
- [ElevenLabs voice recording (audio)](https://previews.sociaro.com/shared/promo/home/presenter-voice-22b95feb.mp3) · [Thumbnail](https://previews.sociaro.com/shared/promo/gallery/creative/presenter-recording-waveform-3bfe60b6.webp)

### After the last train

A Japanese line delivered on a rainy street, with neon light across the speaker’s face.

[Result (video)](https://previews.sociaro.com/shared/promo/p-video-2-pro-avatar/rain.mp4) · [Poster](https://previews.sociaro.com/shared/promo/p-video-2-pro-avatar/rain.jpg) · [Provider example](https://docs.pruna.ai/en/stable/docs_pruna_endpoints/performance_models/p-video-2-pro-avatar.html)

Spoken script (ja)

> 終電、逃した。傘は店に置いてきた。まあ、いいか。

Source inputs

- [Source portrait (image)](https://previews.sociaro.com/shared/promo/gallery/creative/rain-portrait-bdd278d8.jpg) · [Thumbnail](https://previews.sociaro.com/shared/promo/gallery/creative/rain-portrait-thumb.webp)

### A talking fox

A fox in a jacket delivers a line from a single portrait.

[Result (video)](https://previews.sociaro.com/shared/promo/p-video-2-pro-avatar/fox.mp4) · [Poster](https://previews.sociaro.com/shared/promo/p-video-2-pro-avatar/fox.jpg) · [Provider example](https://docs.pruna.ai/en/stable/docs_pruna_endpoints/performance_models/p-video-2-pro-avatar.html)

Spoken script

> I took the good cushion. The other one smells like the dog. That's the whole argument.

Source inputs

- [Source portrait (image)](https://previews.sociaro.com/shared/promo/gallery/creative/fox-portrait-a0255c1f.jpg) · [Thumbnail](https://previews.sociaro.com/shared/promo/gallery/creative/fox-portrait-thumb.webp)

### At Versailles

A seated figure from a royal portrait speaks French and rises.

[Result (video)](https://previews.sociaro.com/shared/promo/p-video-2-pro-avatar/louis.mp4) · [Poster](https://previews.sociaro.com/shared/promo/p-video-2-pro-avatar/louis.jpg) · [Provider example](https://docs.pruna.ai/en/stable/docs_pruna_endpoints/performance_models/p-video-2-pro-avatar.html)

Spoken script (fr)

> Les enfants, à Versailles je me levais avant tout le monde. Pas par vertu. Si je dormais, la cour décidait sans moi. Alors je me levais.

Source inputs

- [Source portrait (image)](https://previews.sociaro.com/shared/promo/gallery/creative/louis-portrait-2971cd4b.jpg) · [Thumbnail](https://previews.sociaro.com/shared/promo/gallery/creative/louis-portrait-thumb.webp)
