its-a-skill-issue/superpowers

talking-head-production

Talking head video production with AI avatars, lipsync, and voiceover.

View source

How to use

  1. Copy the installation command and review the source package before installing it in your own agent environment.
  2. Check the source document for required tools, credentials and supported hosts.
  3. Describe your input and desired deliverable; review the output against the source material.
npx skills add https://github.com/its-a-skill-issue/superpowers --skill talking-head-production

Before you start

  • Installation does not include a model subscription, API allowance or permission to access your files.
  • Repository stars and installation counts describe activity, not an independent quality or security test.
Original skill document

Rendered from the source repository. Headings, examples, code, tables, links, and referenced images are preserved.

Install the belt CLI skill: npx skills add belt-sh/cli

Talking Head Production

Create talking head videos with AI avatars and lipsync via inference.sh CLI.

Quick Start

Requires inference.sh CLI (belt). Install instructions
bash
belt login

# Recommended: P-Video-Avatar (built-in TTS, fastest, cheapest)
belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "Welcome to our product tour. Today I will show you three features that will save you hours every week.",
  "voice": "Zephyr (Female)"
}'

Portrait Requirements

The source portrait image is critical. Poor portraits = poor video output.

Must Have

RequirementWhySpec
Center-framedAvatar needs face in predictable positionFace centered in frame
Head and shouldersBody visible for natural gesturesCrop below chest
Eyes to cameraCreates connection with viewerDirect frontal gaze
Neutral expressionStarting point for animationSlight smile OK, not laughing/frowning
Clear faceModel needs to detect featuresNo sunglasses, heavy shadows, or obstructions
High resolutionDetail preservationMin 512x512 face region, ideally 1024x1024+

Generate a Portrait

bash
# Generate a professional portrait with P-Image
belt app run pruna/p-image --input '{
  "prompt": "professional headshot portrait of a friendly business person, soft studio lighting, clean grey background, head and shoulders, direct eye contact, neutral pleasant expression, photorealistic",
  "aspect_ratio": "9:16"
}'

Background Options

TypeWhen to Use
Solid colorProfessional, clean, easy to composite
Soft bokehNatural, lifestyle feel
Office/studioBusiness context
Dynamic (P-Video-Avatar)Use video_prompt to set background

Model Selection

Start with P-Video-Avatar — it's 18x faster and 6x cheaper than alternatives, with built-in TTS.

ModelApp IDBuilt-in TTSBest For
P-Video-Avatarpruna/p-video-avatarYes (30 voices, 10 langs)Best overall: speed, cost, quality
OmniHuman 1.5bytedance/omnihuman-1-5NoMulti-character, gestures
OmniHuman 1.0bytedance/omnihuman-1-0NoSingle character
Fabric 1.0falai/fabric-1-0YesImage talks with lipsync
PixVerse Lipsyncfalai/pixverse-lipsyncNoRealistic lipsync

Cost & Speed Comparison

ModelSpeed (per sec of video)Cost per second
P-Video-Avatar~1.83s/s$0.025
OmniHuman 1.5~28s/s (15x slower)$0.16 (6.4x more)
Fabric 1.0~34s/s (18x slower)$0.14 (5.6x more)

Production Workflows

Simple: Text Script -> Video (P-Video-Avatar)

No separate TTS step needed — P-Video-Avatar has built-in voices:

bash
belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "Hi there! I am excited to share something with you today.",
  "voice": "Puck (Male)",
  "voice_language": "English (US)",
  "resolution": "720p"
}'

With Style Control

bash
belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "This is exciting news for our community!",
  "voice": "Aoede (Female)",
  "voice_prompt": "Enthusiastic and energetic tone, slightly faster pace",
  "video_prompt": "The person is presenting on stage with dramatic lighting",
  "resolution": "1080p"
}'

Audio-Driven (Any Model)

Provide your own audio file:

bash
# P-Video-Avatar with custom audio
belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "audio": "https://speech.mp3"
}'

# OmniHuman with custom audio
belt app run bytedance/omnihuman-1-5 --input '{
  "image_url": "https://portrait.jpg",
  "audio_url": "https://speech.mp3"
}'

Full Workflow: Generate Portrait + Avatar

bash
# 1. Generate a portrait image
belt app run pruna/p-image --input '{
  "prompt": "professional headshot portrait of a young woman, neutral background, looking at camera, studio lighting, photorealistic",
  "aspect_ratio": "9:16"
}'

# 2. Create avatar video with built-in TTS
belt app run pruna/p-video-avatar --input '{
  "image": "<image-url-from-step-1>",
  "voice_script": "Hi there! Let me walk you through our latest features.",
  "voice": "Zephyr (Female)"
}'

With Separate TTS (for non-TTS models)

bash
# 1. Generate speech
belt app run falai/dia-tts --input '{
  "prompt": "[S1] Your narration script here."
}'

# 2. Create talking head
belt app run bytedance/omnihuman-1-5 --input '{
  "image_url": "https://portrait.jpg",
  "audio_url": "<audio-url-from-step-1>"
}'

Multi-Character Conversation

OmniHuman 1.5 supports up to 2 characters:

bash
# 1. Generate dialogue with two speakers
belt app run falai/dia-tts --input '{
  "prompt": "[S1] So tell me about the new feature. [S2] Sure! We built a dashboard that shows real-time analytics. [S1] That sounds great. How long did it take? [S2] About two weeks from concept to launch."
}'

# 2. Create video with two characters
belt app run bytedance/omnihuman-1-5 --input '{
  "image_url": "https://two-person-portrait.png",
  "audio_url": "<audio-url>"
}'

Long-Form (Stitched Clips)

For content longer than ~60 seconds, split into segments:

bash
# Generate clips with same portrait for consistency
belt app run pruna/p-video-avatar --input '{"image": "https://portrait.jpg", "voice_script": "Segment one..."}' --no-wait
belt app run pruna/p-video-avatar --input '{"image": "https://portrait.jpg", "voice_script": "Segment two..."}' --no-wait
belt app run pruna/p-video-avatar --input '{"image": "https://portrait.jpg", "voice_script": "Segment three..."}' --no-wait

# Merge all segments
belt app run infsh/media-merger --input '{
  "media": ["segment1.mp4", "segment2.mp4", "segment3.mp4"]
}'

Multilingual Content

P-Video-Avatar supports 10 languages with built-in TTS:

bash
# Spanish
belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "Bienvenidos a nuestra demostración de producto.",
  "voice": "Kore (Female)",
  "voice_language": "Spanish"
}'

# Japanese
belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "こんにちは、製品デモへようこそ。",
  "voice": "Leda (Female)",
  "voice_language": "Japanese"
}'

Dub Existing Video

bash
# 1. Transcribe original video
belt app run infsh/fast-whisper-large-v3 --input '{"audio_url": "https://video.mp4"}'

# 2. Translate text (manually or with LLM)

# 3. Generate speech in new language
belt app run infsh/kokoro-tts --input '{"text": "<translated-text>"}'

# 4. Lipsync original video with new audio
belt app run infsh/latentsync-1-6 --input '{
  "video_url": "https://original-video.mp4",
  "audio_url": "<new-audio-url>"
}'

Audio Quality (for non-TTS workflows)

When providing your own audio, quality directly impacts lipsync accuracy.

ParameterTargetWhy
Background noiseNone/minimalNoise confuses lipsync timing
VolumeConsistent throughoutPrevents sync drift
Sample rate44.1kHz or 48kHzStandard quality
FormatMP3 128kbps+ or WAVCompatible with all tools

Available Voices (P-Video-Avatar)

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

Languages: English (US), English (UK), Spanish, French, German, Italian, Portuguese (Brazil), Japanese, Korean, Hindi

Framing Guidelines

┌─────────────────────────────────┐
│          Headroom (minimal)     │
│  ┌───────────────────────────┐  │
│  │                           │  │
│  │     ● ─ ─ Eyes at 1/3 ─ ─│─ │ ← Eyes at top 1/3 line
│  │    /|\                    │  │
│  │     |   Head & shoulders  │  │
│  │    / \  visible           │  │
│  │                           │  │
│  └───────────────────────────┘  │
│       Crop below chest          │
└─────────────────────────────────┘

Common Mistakes

MistakeProblemFix
Low-res portraitBlurry face, poor lipsyncUse 1024x1024+ face region
Profile/side angleLipsync can't track mouth wellUse frontal or near-frontal
Noisy audioLipsync drifts, looks unnaturalUse built-in TTS or record clean
Too-long clipsQuality degradesSplit into segments, stitch
Sunglasses/obstructionFace features hiddenClear face required
Inconsistent lightingUncanny when animatedEven, soft lighting

Related Skills

bash
# Dedicated P-Video-Avatar skill
npx skills add inference-sh/skills@p-video-avatar

# All avatar models
npx skills add inference-sh/skills@ai-avatar-video

# All video generation models
npx skills add inference-sh/skills@ai-video-generation

# Text-to-speech
npx skills add inference-sh/skills@text-to-speech

# Image generation (for portraits)
npx skills add inference-sh/skills@ai-image-generation

Browse all apps: belt app list

from this repository

More skills

All skills
its-a-skill-issue
Community

ai-image-generation

Generate AI images with GPT-Image-2.6, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2.6 Flare, GPT-Image-2.6 Sunburst, FLUX Dev LoRA, FLUX.2 Klein LoRA, Nano Banana 2.1, Gemini 3 Pro Image, Grok Imagine 2.0, Seedream 5.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Trigge

Total installs
619.8K
GitHub stars
0
Updated
Nov 18
its-a-skill-issue
Community

ai-avatar-video

Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars, NPC di

Total installs
619.7K
GitHub stars
0
Updated
Nov 18
its-a-skill-issue
Community

ai-video-generation

Generate AI videos with Google Veo, Seedance 2.5, Kling, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Seedance 2.5, Kling v4, Runway Gen-4.5, FLUX 3 Video, HappyHorse 1.0, Wan 2.7, Grok Imagine Video 1.5, P-Video 2, OmniHuman, Fabric. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Tri

Total installs
619.5K
GitHub stars
0
Updated
Nov 18
its-a-skill-issue
Community

twitter-automation

Automate Twitter/X with posting, engagement, and user management via inference.sh CLI. Apps: x/post-create (text and media), x/post-like, x/post-retweet, x/dm-send, x/user-follow. Capabilities: post tweets, schedule content, like posts, retweet, send DMs, follow users, get profiles. Use for: social media automation, content scheduling, engagement bots, audience growth, X API. Triggers: twitter api, x api, tweet automation, post to twitter, twitter bot, social media automation, x automation, twee

Total installs
619.7K
GitHub stars
0
Updated
Nov 18