Talking Head Production

Talking head video production with AI avatars, lipsync, and voiceover. Covers portrait requirements, audio quality, OmniHuman, PixVerse lipsync, Dia TTS. Use...

Security Scan

The skill's instructions fit its stated purpose (making talking‑head videos) but they direct you to download-and-run a remote installer from unfamiliar domains and to upload media to third‑party inference services without documenting credentials, privacy, or provenance — this mismatch and install risk merit caution.

Purpose & Capability

The name, description and runtime instructions consistently describe generating TTS, lipsync and avatar videos via the infsh CLI and specific apps (falai, bytedance). The requested operations (generate audio, run OmniHuman, PixVerse lipsync) align with the stated purpose.

Instruction Scope

SKILL.md instructs the agent/user to curl|sh a remote installer and to run infsh commands that will read local media files and submit them to remote apps. It does not instruct reading unrelated system files, but it implicitly requires logging into inference.sh and uploading potentially sensitive media without documenting privacy, storage, or retention policies.

Install Mechanism

Although the registry has no formal install spec, SKILL.md tells users to run curl -fsSL https://cli.inference.sh | sh which is a high‑risk pattern (download-and-execute). The domains (cli.inference.sh, dist.inference.sh) are not standard well-known release hosts like GitHub releases; the doc claims checksum verification but the initial bootstrap still executes remote script — this is disproportionate risk for an instruction-only skill.

Credentials

The skill declares no required env vars, which is consistent, but it calls infsh login (implying credentials are needed) and invokes third‑party apps (bytedance, falai). The skill does not declare where credentials are stored, what scopes are required, or whether user media will be uploaded to third parties — this lack of detail about credentials and data handling is a proportionality/privacy concern.

Persistence & Privilege

The skill is not always-included and does not request elevated platform privileges. It does cause installation of an external CLI (per SKILL.md), but it does not request to modify other skills or system-wide config in the documented instructions.

Scan Findings in Context

[no_regex_findings] expected: The static scanner found no code to analyze; the package is instruction-only (SKILL.md). Absence of findings is expected but provides limited signal — the installer invoked by the instructions was not scanned.

What to consider before installing

This skill appears to do what it claims (create talking‑head videos) but it directs you to run a remote installer (curl | sh) from cli.inference.sh and to upload images/audio to third‑party inference services. Before installing or running anything: (1) do not run curl | sh from an unfamiliar domain without verifying the source — prefer official release pages or GitHub releases and verify checksums yourself; (2) research the inference.sh service (privacy, data retention, who runs dist.inference.sh), and create a throwaway/test account first if you want to experiment; (3) confirm where and how infsh stores login credentials and what scopes the login grants; (4) avoid uploading sensitive personal data (faces, private audio) until you’ve confirmed data handling policies; (5) consider running the CLI in a sandbox or VM and inspect the installer script before executing. If you want, provide the cli.inference.sh and dist.inference.sh URLs or any homepage/source repository you can find and I can review those artifacts for stronger assurance.

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

Quick Start

curl -fsSL https://cli.inference.sh | sh && infsh login

# Generate dialogue audio
infsh app run falai/dia-tts --input '{
  "prompt": "[S1] Welcome to our product tour. Today I will show you three features that will save you hours every week."
}'

# Create talking head video with OmniHuman
infsh app run bytedance/omnihuman-1-5 --input '{
  "image": "path/to/portrait.png",
  "audio": "path/to/dialogue.mp3"
}'

Install note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available.

Portrait Requirements

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

Must Have

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+

Background

Type	When to Use
Solid color	Professional, clean, easy to composite
Soft bokeh	Natural, lifestyle feel
Office/studio	Business context
Transparent (via bg removal)	Compositing into other scenes

# Generate a professional portrait background
infsh app run falai/flux-dev-lora --input '{
  "prompt": "professional headshot photograph of a friendly business person, soft studio lighting, clean grey background, head and shoulders, direct eye contact, neutral pleasant expression, high quality portrait photography"
}'

# Or remove background from existing portrait
infsh app run <bg-removal-app> --input '{
  "image": "path/to/portrait-with-background.png"
}'

Audio Quality

Audio quality directly impacts lipsync accuracy. Clean audio = accurate lip movement.

Requirements

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

Generating Audio

# Simple narration
infsh app run falai/dia-tts --input '{
  "prompt": "[S1] Hi there! I am excited to share something with you today. We have been working on a feature that our users have been requesting for months... and it is finally here."
}'

# With emotion and pacing
infsh app run falai/dia-tts --input '{
  "prompt": "[S1] You know what is frustrating? Spending hours on tasks that should take minutes. (sighs) We have all been there. But what if I told you... there is a better way?"
}'

Model Selection

Model	App ID	Best For	Max Duration
OmniHuman 1.5	bytedance/omnihuman-1-5	Multi-character, gestures, high quality	~30s per clip
OmniHuman 1.0	bytedance/omnihuman-1-0	Single character, simpler	~30s per clip
PixVerse Lipsync	falai/pixverse-lipsync	Quick lipsync on existing video	Short clips
Fabric	falai/fabric-1-0	Cloth/fabric animation on portraits	Short clips

Production Workflows

Basic: Portrait + Audio -> Video

# 1. Generate or prepare audio
infsh app run falai/dia-tts --input '{
  "prompt": "[S1] Your narration script here."
}'

# 2. Generate talking head
infsh app run bytedance/omnihuman-1-5 --input '{
  "image": "portrait.png",
  "audio": "narration.mp3"
}'

With Captions

# 1-2. Same as above

# 3. Add captions to the talking head video
infsh app run infsh/caption-videos --input '{
  "video": "talking-head.mp4",
  "caption_file": "captions.srt"
}'

Long-Form (Stitched Clips)

For content longer than 30 seconds, split into segments:

# Generate audio segments
infsh app run falai/dia-tts --input '{"prompt": "[S1] Segment one script."}' --no-wait
infsh app run falai/dia-tts --input '{"prompt": "[S1] Segment two script."}' --no-wait
infsh app run falai/dia-tts --input '{"prompt": "[S1] Segment three script."}' --no-wait

# Generate talking head for each segment (same portrait for consistency)
infsh app run bytedance/omnihuman-1-5 --input '{"image": "portrait.png", "audio": "segment1.mp3"}' --no-wait
infsh app run bytedance/omnihuman-1-5 --input '{"image": "portrait.png", "audio": "segment2.mp3"}' --no-wait
infsh app run bytedance/omnihuman-1-5 --input '{"image": "portrait.png", "audio": "segment3.mp3"}' --no-wait

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

Multi-Character Conversation

OmniHuman 1.5 supports up to 2 characters:

# 1. Generate dialogue with two speakers
infsh 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
infsh app run bytedance/omnihuman-1-5 --input '{
  "image": "two-person-portrait.png",
  "audio": "dialogue.mp3"
}'

Framing Guidelines

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

Common Mistakes

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	Record clean or use TTS
Too-long clips	Quality degrades after 30s	Split into segments, stitch
Sunglasses/obstruction	Face features hidden	Clear face required
Inconsistent lighting	Uncanny when animated	Even, soft lighting
No captions	Loses silent/mobile viewers	Always add captions

Related Skills

npx skills add inference-sh/skills@ai-avatar-video
npx skills add inference-sh/skills@ai-video-generation
npx skills add inference-sh/skills@text-to-speech

Browse all apps: infsh app list