Generate talking head avatar videos with Pruna P-Video-Avatar via inference.sh CLI. Turn a portrait image into a realistic speaking video with built-in TTS. 18x faster and 6x cheaper than competitors. Models: P-Video-Avatar, P-Image (for portrait generation). Capabilities: text-to-avatar, audio-driv

Install the belt CLI skill: npx skills add belt sh/cli Pruna P Video Avatar Generate talking head avatar videos from a single portrait image via [inference.sh](https://inference.sh) CLI. P Video Avatar is the fastest and most cost effective avatar video model available. Quality on par with Veo 3.0, 18x faster and 6x cheaper than alternatives like Fabric, OmniHuman, and HeyGen. Quick Start Requires inference.sh CLI ( belt ). [Install instructions](https://raw.githubusercontent.com/inference sh/skills/refs/heads/main/cli install.md) Full Workflow: Generate Portrait + Avatar Video Use Pruna P Image to generate the portrait, then P Video Avatar to animate it: Examples Text Script with Voice Selection Audio Driven Avatar Provide your own audio file instead of using built in TTS: When both audio and voice script are provided, audio takes priority. 1080p with Custom Style Multilingual Content Reproducible Generation Available Voices Female: Zephyr, Kore, Leda, Aoede, Callirrhoe, Autonoe, Despina, Erinome, Laomedeia, Achernar, Gacrux, Pulcherrima, Vindemiatrix, Sulafat Male: Puck, Charon, Fenrir, Orus, Enceladus, Iapetus, Umbriel, Algenib, Algieba, Schedar, Achird, Zubenelgenubi, Sadachbia, Sadaltager, Alnilam, Rasalgethi Supported Languages English (US), English (UK), Spanish, French, German, Italian, Portuguese (Brazil), Japanese, Korean, Hindi Parameters Parameter Type Default Description image file required Portrait image (jpg, jpeg, png, webp) voice script string Text for the person to say audio file Audio file (overrides voice script) voice string "Zephyr (Female)" Voice selection voice language string "English (US)" Output language resolution string "720p" 720p or 1080p video prompt string "The person is talking." Control avatar behavior and background voice prompt string "Say the following." Control tone, pacing, emotion seed int random Reproducible generation disable safety filter bool true Disable content filter disable prompt upsampling bool false Skip prompt enhancement Pricing Resolution Price 720p $0.025 per second of output video 1080p $0.045 per second of output video Example: 30 second 720p video = $0.75 Free Launch Weekend P Video Avatar is completely free from Thursday May 1, 2026 4:00 PM CET through Sunday May 4, 2026 11:59 PM CET. All costs are on us during this window — no billing, no limits on resolution. Competitive Advantage Feature P Video Avatar Fabric 1.0 OmniHuman 1.5 HeyGen Avatar 4 Speed (per sec of video) ~1.83s/s ~34s/s (18x slower) ~28s/s (15x slower) ~26s/s (14x slower) Cost per second $0.025 $0.14 (5.6x more) $0.16 (6.4x more) $0.075 (3x more) Built in TTS Yes Yes No Yes Dynamic Background Yes Yes No Yes 1080p Support Yes No No Yes Use Cases Marketing : Product demos, UGC style ads with AI presenters Education : Course videos, explainers, tutoring content Localization : Dub content across 10 languages from one image Social Media : Consistent virtual influencer content Corporate : Training, onboarding, announcements Gaming : Character avatars, NPC dialogue videos Customer Support : Personalized video responses Tips Use high quality portrait photos (front facing, good lighting) The output video aspect ratio matches the input image Use video prompt to control dynamic backgrounds and body language Use voice prompt to control speaking style, emotion, and pacing Keep videos under 3 minutes for best visual consistency Generate portraits with pruna/p image using aspect ratio 9:16 for vertical avatar videos Related Pruna Models Related Skills Browse all Pruna apps: belt app list search "pruna" Documentation [Running Apps](https://inference.sh/docs/apps/running) How to run apps via CLI [Streaming Results](https://inference.sh/docs/api/sdk/streaming) Real time progress updates [Content Pipeline Example](https://inference.sh/docs/examples/content pipeline) Building media workflows

p-video-avatar