HeyGen
1 Tool · 9 Intel
HeyGen is a generative AI company known for photo-realistic video avatars, offering a library of pre-made avatars and voices alongside tools for creating custom ones from user photos and video. Founded by Joshua Xu and Wayne Liang in 2020, the company is headquartered in Los Angeles and has raised funding from investors including Sequoia China (HongShan), ZhenFund, and Conviction.
Is this you? Sign in with X to claim this profile.
Tools
Framework that renders HTML, CSS, and animations into deterministic MP4 videos via CLI or AI agent skills.
Intel
HeyGen previews a Professional Voice Clone API that trains a dedicated voice model from twenty minutes of speaker audio, closing the voice-realism gap for avatar video generation.
HeyGen released Video 1, its first general-purpose video model. It takes a prompt, image or reference and returns 2K shots with sound and dialogue, mostly in under a minute, priced from one cent per second, on the HeyGen app and API.
A walkthrough of connecting Meta's Muse Agent, a persistent cloud agent that schedules its own recurring cron jobs, to HeyGen's MCP server so it drafts scripts and generates avatar videos, gated behind a human approval step before each render.
A field guide to HeyGen's MCP server: how it turns video generation into a callable agent tool, what tools it exposes (generate, browse assets, check render status and credits), and how to chain it with other connectors like Notion or a CRM.
A detailed walkthrough of using Claude Cowork's MCP connectors to pull a week of Slack messages, pitch video ideas, write a script, and hand it to HeyGen for a render, explaining Cowork's September 2026 merge into the main Claude app.
HeyGen says its Voice Turbo and Voice models hold the top two spots on the Artificial Analysis text-to-speech leaderboard. The faster, cheaper Turbo endpoint is live on the API and free through November 30. The ranking is self-reported.
HeyGen launches HeyGen Video, a business-oriented video model built on MiniMax H3 and post-trained in-house. The API lists $0.03/s with a 50% launch discount, claims faster inference than its base model, and ships with MCP, CLI and llms.txt for agents.
A walkthrough of pairing TypeSafe's Jev decision model with the HeyGen MCP. Jev returns typed probabilities with confidence for sub-cent triage, so Claude drafts scripts and HeyGen renders only shortlisted leads.
HeyGen released HeyGen Voice, a TTS model that tops Artificial Analysis's controlled-voice arena at 1199 Elo, ahead of Qwen-Audio-3.1-TTS-Plus and Eleven v4. It is live in the app and API at half price ($15 per million characters) through October 31.