cinemasetfreeprunaai/p-video-2-pro-avatar
Pruna's talking-avatar model. Turn a portrait and an audio file or script into a talking video with synced lips and expressions, from 1 second to 3 minutes long.
Capabilities
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
image* | string(uri) | Portrait of the person who speaks (first frame). Supports jpg, jpeg, png, webp. | — | — |
audio | string(uri) | Speech audio, up to 3 minutes; the video matches its length. Overrides voice_script. | — | — |
enable_safety_filter | boolean | Block content in the toggleable moderation categories. The always-on rules apply either way. | false | — |
prompt | string | What the video should show. | "The person is talking." | — |
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. | true | — |
resolution | string | Video resolution. 1080p, 2k and 4k generate at 768p and upscale it (24 fps kept); 4k is limited to 125 s of audio. | "768p" | 480p768p1080p2k4k |
seed | integer | Random seed for reproducible generation. | — | — |
voice | string | Gemini TTS voice for voice_script. | "Zephyr (Female)" | Zephyr (Female)Puck (Male)Charon (Male)Kore (Female)Fenrir (Male)Leda (Female)Orus (Male)Aoede (Female)Callirrhoe (Female)Autonoe (Female)Enceladus (Male)Iapetus (Male)Umbriel (Male)Algenib (Male)Despina (Female)Erinome (Female)Laomedeia (Female)Achernar (Female)Algieba (Male)Schedar (Male)Gacrux (Female)Pulcherrima (Female)Achird (Male)Zubenelgenubi (Male)Vindemiatrix (Female)Sadachbia (Male)Sadaltager (Male)Sulafat (Female)Alnilam (Male)Rasalgethi (Male) |
voice_language | string | Language of voice_script. | "English (US)" | English (US)English (UK)SpanishFrenchGermanItalianPortuguese (Brazil)JapaneseKoreanHindi |
voice_prompt | string | Delivery instructions for the TTS voice (tone, pacing, accent, emotion). Not spoken. | "Say the following." | — |
voice_script | string | Exact words to speak with Gemini TTS. Required when no audio is uploaded. | "" | — |
imagerequiredstringPortrait of the person who speaks (first frame). Supports jpg, jpeg, png, webp.
audiostringSpeech audio, up to 3 minutes; the video matches its length. Overrides voice_script.
enable_safety_filterbooleanBlock content in the toggleable moderation categories. The always-on rules apply either way.
falsepromptstringWhat the video should show.
"The person is talking."prompt_upsamplingbooleanLet 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.
trueresolutionstringVideo resolution. 1080p, 2k and 4k generate at 768p and upscale it (24 fps kept); 4k is limited to 125 s of audio.
"768p"seedintegerRandom seed for reproducible generation.
voicestringGemini TTS voice for voice_script.
"Zephyr (Female)"voice_languagestringLanguage of voice_script.
"English (US)"voice_promptstringDelivery instructions for the TTS voice (tone, pacing, accent, emotion). Not spoken.
"Say the following."voice_scriptstringExact words to speak with Gemini TTS. Required when no audio is uploaded.
""f18ad1e8300aUpdated: 11/7/202620.2K runs