cinemasetfree.comprunaai/p-video-avatar
p-video-avatar is the fastest and cheapest avatar/lipsync video model on the market.
Capabilities
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
image* | string(uri) | Input image (first frame). Supports jpg, jpeg, png, webp. | — | — |
audio | string(uri) | Optional uploaded audio to drive avatar speech. If provided, this is used instead of voice_script and voice settings. | — | — |
disable_prompt_upsampling | boolean | When true, skip automatic enhancement of the visual video prompt and use video_prompt directly. | false | — |
disable_safety_filter | boolean | Disable safety filter for prompts and input image. When disabled, prompts are not checked for unsafe content before generation. | true | — |
negative_prompt | string | Disabled if empty.Mention what you do NOT want in the video, e.g. "subtitles, text, blurry, low quality, frames, watermark, titles, scene change". We recommend using multiple keywords at once. | "" | — |
no_op | boolean | Health check mode - returns status without inference. | false | — |
resolution | string | Resolution of the video. | "720p" | 720p1080p |
seed | integer | Random seed. Set for reproducible generation. | — | — |
strength_negative_prompt | number | Strength of the Negative Prompt. Optimal value can differ for different video lengths (Experimental Feature) | 0.5 | min: 0, max: 4 |
video_prompt | string | Optional visual prompt describing how the person should appear or behave while speaking. | "The person is talking." | — |
voice | string | Voice to use when generating speech from 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/accent target for generated speech. | "English (US)" | English (US)English (UK)SpanishFrenchGermanItalianPortuguese (Brazil)JapaneseKoreanHindi |
voice_prompt | string | Optional style instructions for how to speak voice_script, such as tone, pacing, accent, or emotion. These instructions are not spoken. | "Say the following." | — |
voice_script | string | Exact words the avatar should say. Required when no audio file is uploaded. | "" | — |
imagerequiredstringInput image (first frame). Supports jpg, jpeg, png, webp.
audiostringOptional uploaded audio to drive avatar speech. If provided, this is used instead of voice_script and voice settings.
disable_prompt_upsamplingbooleanWhen true, skip automatic enhancement of the visual video prompt and use video_prompt directly.
falsedisable_safety_filterbooleanDisable safety filter for prompts and input image. When disabled, prompts are not checked for unsafe content before generation.
truenegative_promptstringDisabled if empty.Mention what you do NOT want in the video, e.g. "subtitles, text, blurry, low quality, frames, watermark, titles, scene change". We recommend using multiple keywords at once.
""no_opbooleanHealth check mode - returns status without inference.
falseresolutionstringResolution of the video.
"720p"seedintegerRandom seed. Set for reproducible generation.
strength_negative_promptnumberStrength of the Negative Prompt. Optimal value can differ for different video lengths (Experimental Feature)
0.5min: 0, max: 4video_promptstringOptional visual prompt describing how the person should appear or behave while speaking.
"The person is talking."voicestringVoice to use when generating speech from voice_script.
"Zephyr (Female)"voice_languagestringLanguage/accent target for generated speech.
"English (US)"voice_promptstringOptional style instructions for how to speak voice_script, such as tone, pacing, accent, or emotion. These instructions are not spoken.
"Say the following."voice_scriptstringExact words the avatar should say. Required when no audio file is uploaded.
""8a54bb678ef4Updated: 7/25/202657.8K runs