talking-head-production
Talking head video production with AI avatars, lipsync, and voiceover. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also covers OmniHuman, PixVerse, Fabric. Portrait requirements, audio quality, production workflows. Use for: spokesperson videos, course content, social media, pr...
Full skill instructions
Install the belt CLI skill:
npx skills add belt-sh/cli
Create talking head videos with AI avatars and lipsync via inference.sh CLI.
Requires inference.sh CLI (
belt). Install instructions
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)"
}'
The source portrait image is critical. Poor portraits = poor video output.
| Requirement | Why | Spec |
|---|---|---|
| Center-framed | Avatar needs face in predictable position | Face centered in frame |
| Head and shoulders | Body visible for natural gestures | Crop below chest |
| Eyes to camera | Creates connection with viewer | Direct frontal gaze |
| Neutral expression | Starting point for animation | Slight smile OK, not laughing/frowning |
| Clear face | Model needs to detect features | No sunglasses, heavy shadows, or obstructions |
| High resolution | Detail preservation | Min 512x512 face region, ideally 1024x1024+ |
# 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"
}'
| Type | When to Use |
|---|---|
| Solid color | Professional, clean, easy to composite |
| Soft bokeh | Natural, lifestyle feel |
| Office/studio | Business context |
| Dynamic (P-Video-Avatar) | Use video_prompt to set background |
Start with P-Video-Avatar — it's 18x faster and 6x cheaper than alternatives, with built-in TTS.
| Model | App ID | Built-in TTS | Best For |
|---|---|---|---|
| P-Video-Avatar | pruna/p-video-avatar | Yes (30 voices, 10 langs) | Best overall: speed, cost, quality |
| OmniHuman 1.5 | bytedance/omnihuman-1-5 | No | Multi-character, gestures |
| OmniHuman 1.0 | bytedance/omnihuman-1-0 | No | Single character |
| Fabric 1.0 | falai/fabric-1-0 | Yes | Image talks with lipsync |
| PixVerse Lipsync | falai/pixverse-lipsync | No | Realistic lipsync |
| Model | Speed (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) |
No separate TTS step needed — P-Video-Avatar has built-in voices:
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"
}'
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"
}'
Provide your own audio file:
# 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"
}'
# 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)"
}'
# 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>"
}'
OmniHuman 1.5 supports up to 2 characters:
# 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>"
}'
For content longer than ~60 seconds, split into segments:
# 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"]
}'
P-Video-Avatar supports 10 languages with built-in TTS:
# 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"
}'
# 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>"
}'
When providing your own audio, quality directly impacts lipsync accuracy.
| Parameter | Target | Why |
|---|---|---|
| Background noise | None/minimal | Noise confuses lipsync timing |
| Volume | Consistent throughout | Prevents sync drift |
| Sample rate | 44.1kHz or 48kHz | Standard quality |
| Format | MP3 128kbps+ or WAV | Compatible with all tools |
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
┌─────────────────────────────────┐
│ Headroom (minimal) │
│ ┌───────────────────────────┐ │
│ │ │ │
│ │ ● ─ ─ Eyes at 1/3 ─ ─│─ │ ← Eyes at top 1/3 line
│ │ /|\ │ │
│ │ | Head & shoulders │ │
│ │ / \ visible │ │
│ │ │ │
│ └───────────────────────────┘ │
│ Crop below chest │
└─────────────────────────────────┘
| Mistake | Problem | Fix |
|---|---|---|
| Low-res portrait | Blurry face, poor lipsync | Use 1024x1024+ face region |
| Profile/side angle | Lipsync can't track mouth well | Use frontal or near-frontal |
| Noisy audio | Lipsync drifts, looks unnatural | Use built-in TTS or record clean |
| Too-long clips | Quality degrades | Split into segments, stitch |
| Sunglasses/obstruction | Face features hidden | Clear face required |
| Inconsistent lighting | Uncanny when animated | Even, soft lighting |
# 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 store
Remove backgrounds from images with BiRefNet via inference.sh CLI. Model: BiRefNet (high accuracy background removal). Use for: product photos, portraits, e-commerce, transparent PNGs, photo editing. Triggers: remove background, background removal, remove bg, transparent background, cut out image, background remover, rembg, product photo editing, cutout, transparent png, bg removal, photo cutout
AI voice generation, text-to-speech, and voice synthesis via inference.sh CLI. Models: Inworld TTS-2 (100+ languages, emotion/non-verbal steering), Inworld TTS 1.5 (ultra-low latency), ElevenLabs (22+ premium voices, 32 languages), Kokoro TTS, DIA, Chatterbox, Higgs, VibeVoice for natural speech. Capabilities: multiple voices, emotions, accents, long-form narration, conversation, voice transformation, delivery mode control, character voices. Use for: voiceovers, audiobooks, podcasts, video narration, accessibility, gaming NPCs, avatar audio, UGC. Triggers: voice cloning, tts, text to speech, ai voice, voice generation, voice synthesis, voice over, narration, speech synthesis, ai narrator, elevenlabs, eleven labs, natural voice, realistic speech, voice ai, voice changer, inworld, inworld tts, character voice, npc voice
Generate professional AI product photography and commercial images. Models: FLUX, Imagen 3, Grok, Seedream for product shots, lifestyle images, mockups. Capabilities: studio lighting, lifestyle scenes, packaging, e-commerce photos. Use for: e-commerce, Amazon listings, Shopify, marketing, advertising, mockups. Triggers: product photography, product shot, commercial photography, e-commerce images, amazon product photo, shopify images, product mockup, studio product shot, lifestyle product image, advertising photo, packshot, product render, product image ai
Generate AI music and songs with ElevenLabs, Diffrythm, Tencent Song Generation via inference.sh CLI. Models: ElevenLabs Music (up to 10 min, commercial license), Diffrythm (fast song generation), Tencent Song Generation (full songs with vocals). Capabilities: text-to-music, song generation, instrumental, lyrics to song, soundtrack creation. Use for: background music, social media content, game soundtracks, podcasts, royalty-free music. Triggers: music generation, ai music, generate song, ai composer, text to music, song generator, create music with ai, suno alternative, udio alternative, ai song, ai soundtrack, generate soundtrack, ai jingle, music ai, beat generator, elevenlabs music, eleven labs music
Transcribe audio to text with ElevenLabs Scribe and Whisper models via inference.sh CLI. Models: ElevenLabs Scribe v2 (98%+ accuracy, diarization), Fast Whisper Large V3, Whisper V3 Large. Capabilities: transcription, translation, multi-language, timestamps, speaker diarization, audio event tagging. Use for: meeting transcription, subtitles, podcast transcripts, voice notes. Triggers: speech to text, transcription, whisper, audio to text, transcribe audio, voice to text, stt, automatic transcription, subtitles generation, transcribe meeting, audio transcription, whisper ai, elevenlabs stt, scribe, eleven labs transcribe
JavaScript/TypeScript SDK for inference.sh - run AI apps, build agents, integrate with all models. Package: @inferencesh/sdk (npm install). Full TypeScript support, streaming, file uploads. Build agents with template or ad-hoc patterns, tool builder API, skills, human approval. Use for: JavaScript integration, TypeScript, Node.js, React, Next.js, frontend apps. Triggers: javascript sdk, typescript sdk, npm install, node.js api, js client, react ai, next.js ai, frontend sdk, @inferencesh/sdk, typescript agent, browser sdk, js integration
Upscale and enhance images with Real-ESRGAN, Thera, Topaz, FLUX Upscaler via inference.sh CLI. Models: Real-ESRGAN, Thera (any size), FLUX Dev Upscaler, Topaz Image Upscaler. Use for: enhance low-res images, upscale AI art, restore old photos, increase resolution. Triggers: upscale image, image upscaler, enhance image, increase resolution, real esrgan, ai upscale, super resolution, image enhancement, upscaling, enlarge image, higher resolution, 4k upscale, hd upscale
SEO content brief creation with keyword research, search intent analysis, and content structure. Covers SERP analysis, heading hierarchy, word count targets, and internal linking strategy. Use for: content briefs, SEO writing, blog strategy, content planning, keyword targeting. Triggers: seo content brief, content brief, seo brief, keyword research, search intent, content strategy, blog brief, seo writing, content planning, keyword targeting, serp analysis, content outline, seo article, blog seo
Python SDK for inference.sh - run AI apps, build agents, and integrate with all models. Package: inferencesh (pip install inferencesh). Supports sync/async, streaming, file uploads. Build agents with template or ad-hoc patterns, tool builder API, skills, and human approval. Use for: Python integration, AI apps, agent development, RAG pipelines, automation. Triggers: python sdk, inferencesh, pip install, python api, python client, async inference, python agent, tool builder python, programmatic ai, python integration, sdk python
Data visualization with chart selection, color theory, and annotation best practices. Covers chart types (bar, line, scatter, heatmap), axes rules, and storytelling with data. Use for: charts, graphs, dashboards, reports, presentations, infographics, data stories. Triggers: data visualization, chart, graph, data chart, bar chart, line chart, scatter plot, data viz, visualization, dashboard chart, infographic data, data presentation, chart design, plot, heatmap, pie chart alternative
Research-backed customer persona creation with market data and avatar generation. Covers demographics, psychographics, jobs-to-be-done, journey mapping, and anti-personas. Use for: marketing strategy, product development, UX research, sales enablement, content strategy. Triggers: customer persona, buyer persona, user persona, target audience, ideal customer, customer profile, audience research, user research, icp, ideal customer profile, target market, customer avatar, audience persona
Generate images with Google Gemini 3.1 Flash Image Preview (Nano Banana 2) via inference.sh CLI. Capabilities: text-to-image, image editing, multi-image input (up to 14 images), Google Search grounding. Triggers: nano banana 2, nanobanana 2, gemini 3.1 flash image, gemini 3 1 flash image preview, google image generation
Generate, edit, and beat-sync AI video with leading models in one workspace.
The world's fastest calendar for remote work
Transform Your Design with AI Designer by ImgCreator.ai
Revolutionizing Video Production with AI-Powered Creativity
Extend an image past the frame and let AI fill the new aspect ratio.
Discover your celebrity doppelgänger with StarByFace!
ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.
Opus.ai: Revolutionize Your Web Experience