Automated avatar-video production
Generate repeatable onboarding, product, training, or campaign videos from approved scripts and structured inputs.
Independent tool overview
HeyGen CLI is an official command-line client for automating HeyGen avatar videos, translation, and lip sync through the v3 API. It is useful for scripts and agents, but every production workflow still needs secure credential handling, asynchronous job checks, output review, and API-cost controls.
Visit the official HeyGen CLI site ↗
Overview
HeyGen CLI brings HeyGen's video platform into terminals, scripts, continuous-integration jobs, containers, and AI-agent workflows. It wraps the v3 API and returns structured JSON by default, so a program can create a video, capture its ID, poll the job, and download the completed asset without driving the web editor.
Users can generate a complete prompted video through Video Agent or send a detailed JSON body that selects an avatar, voice, script, and other parameters. The CLI also covers video translation and lip sync, exposes request schemas without authentication, and offers blocking or asynchronous job handling.
The CLI itself does not have a separate subscription. API-key authentication draws from HeyGen's prepaid API wallet, which starts with a $5 top-up and is separate from normal web-plan credits. OAuth can instead bill supported usage to an eligible web plan. This distinction matters when estimating automation costs.
Use cases
The strongest fit depends on the job you need the product to complete, not the size of its feature list.
Generate repeatable onboarding, product, training, or campaign videos from approved scripts and structured inputs.
Use JSON output, exit codes, environment-based authentication, and polling to integrate video generation into programmatic jobs.
Submit translations or lip-sync jobs, track their status, and download completed localized assets without manual editor work.
Capabilities
Video Agent can choose an avatar, voice, and layout from one prompt, then return a session and video ID while generation continues.
The lower-level video command accepts structured bodies for developers who need explicit control over avatar, voice, script, and other fields.
Structured JSON is the default, with additional output modes for streaming, readable terminal output, and machine processing.
Create commands can return immediately for polling or wait until completion with a configurable timeout and documented exit behavior.
The CLI exposes HeyGen's video translation and lip-sync capabilities alongside avatar-video creation.
Commands can print their request schema without authentication, helping scripts and agents build valid payloads.
Process
Step 1
Install the single binary, verify its version, and inspect the request schema for the exact command you plan to automate.
Step 2
Use OAuth interactively or inject the API key through a managed secret in CI; never commit credentials or paste them into logged commands.
Step 3
Use Video Agent for a prompt-led result or a structured JSON body when avatar, voice, script, and layout must be deterministic.
Step 4
Handle pending, processing, completed, and failed states, then review the rendered video before it enters a customer-facing pipeline.
Cost
HeyGen CLI uses the API or eligible web-plan balance rather than a CLI-specific fee. API-key workflows are prepaid pay as you go with a $5 minimum top-up. Rates are based on output duration or operation type, and the API wallet is separate from normal HeyGen web-plan credits.
Starts with a $5 wallet top-up
The self-serve option for CLI automation using an API key, with no monthly API subscription.
$0.0333-$0.0667 per second
Duration-based rates for localizing or lip-syncing existing video.
Usage based
Additional commands can have their own unit rate.
Custom
For organizations that need negotiated scale, support, or restricted endpoints.
Pricing checked . Check current pricing at the source ↗
Assessment
Compare
The right alternative depends on the specific output, workflow, controls and budget your project requires.
Content Creator
Choose the web-based HeyGen Video Agent when a conversational visual workflow matters more than terminal automation.
Explore HeyGen Video Agent →Marketing
Use HeyGen's main creation experience when editors and marketers need a graphical interface rather than scripts.
Explore LiveAvatar by HeyGen →Marketing
Consider Synthesia for a mature browser-based enterprise avatar-video workflow with governance and collaboration features.
Explore Synthesia →Content Creator
Consider Tavus when personalized video or real-time conversational video APIs are the central requirement.
Explore tavus →Questions
HeyGen CLI is HeyGen's official command-line client for its v3 video API. It lets developers and agents create, translate, lip-sync, monitor, and download video assets from scripts or terminals.
The binary has no separate listed fee, but generated work consumes HeyGen API balance or eligible web-plan credits. Self-serve API access starts with a $5 pay-as-you-go wallet top-up.
With API-key billing, HeyGen currently lists Video Agent at $0.0333 per output second, which is about $2 per generated minute.
Not natively yet. HeyGen documents macOS and Linux binaries and recommends Windows Subsystem for Linux while native Windows support is pending.
Yes. It defaults to structured JSON, supports environment-based authentication, returns status and failure data, and can either poll asynchronously or wait for a job.
Interactive API-key login stores credentials under ~/.heygen/credentials. In CI, HeyGen supports the HEYGEN_API_KEY environment variable; use a real secret manager and keep the value out of logs and source control.
Bottom line
HeyGen CLI is a practical interface for teams that already want HeyGen output and need repeatable, programmatic video production. Its JSON-first design and job controls are much more automation-friendly than driving the web editor. Start with a short, representative batch, measure cost per accepted minute, and require both automated checks and human review before publishing.
Visit HeyGen CLI website ↗
Avatar V - HeyGen's new AI avatar model that generates studio-quality, hyperrealistic videos from a 15-second clip

ERNIE-Image - Baidu's 8B open-weight text-to-image model that nears top rivals on benchmarks despite its small size

MAI Image 2 - Microsoft AI's image model with upgraded photorealism and creativity

Happy Horse - Alibaba's new SOTA AI video model

Get access to all our AI courses, hundreds of real-world AI use cases, live expert-led workshops, an exclusive network of AI early adopters, and more.
Get unlimited access to all of our current & upcoming industry-specific AI courses for the duration of your subscription.
To keep up with the rapid pace of AI, our team publishes AI implementation guides daily. Our library contains 300+ practical use cases to automate real-world work.
Join weekly, live, interactive sessions with industry leaders who are at the forefront of AI for hands-on implementation guidance and exclusive insights.
Network with an exclusive community of AI-first professionals who are working smarter with AI. Learn how early adopters are using AI in their work and businesses.