Endpoint: /v1/streaming.new
Reference: https://docs.heygen.com/reference/new-session

Add the new session parameter activity_idle_timeout, which defines the maximum idle period—in seconds—after the last user interaction before a session is marked inactive. It defaults to 120 seconds and accepts any value between 30 and 3600 seconds.

Endpoint: /v1/streaming.keep_alive
Reference: https://docs.heygen.com/reference/keep-alive

Introduce a new endpoint to reset the idle‐timeout counter for an active streaming session.

Endpoint: /v1/streaming/knowledge_base/*
Reference: https://docs.heygen.com/reference/list-knowledge-bases

We’ve added new Knowledge Base Management endpoints! You can now list, create, update, and delete knowledge bases for your interactive avatars.

Endpoint: /v2/avatar/{avatar_id}/details
Reference: https://docs.heygen.com/reference/retrieve-avatar-details

We’ve added the Retrieve Avatar Details endpoint! Retrieve detailed information for a specific avatar by providing its avatar_id.

Endpoint: /v2/voices/locales
Reference: https://docs.heygen.com/reference/list-all-locales-for-voices

We’ve added the List All Locales for Voices endpoint! Retrieve a full list of available voice locales (like en-US, pt-BR, etc.) that you can use with multilingual voices when generating videos. Before using, check if the voice supports locales via the support_locale attribute from /v2/voices.

Bring the full power of HeyGen's API to your favorite AI-enabled tools — like Cursor, Claude Desktop, and more — with zero manual implementation. Just install the HeyGen MCP Server and you're ready to go!

🔧 No need to write integration code
🧠 Works seamlessly with AI development environments
💡 Ideal for rapid prototyping and automation

Get started: https://docs.heygen.com/docs/heygen-mcp-server

Endpoint: /v2/streaming.list
Reference: https://docs.heygen.com/reference/list-sessions-v2

We have introduced a new v2 endpoint for listing sessions. This endpoint supports pagination and allows you to retrieve a list of all sessions with optional filtering by date range and status.

We've add support for choosing between Eleven Lab models such as eleven_flash_v2_5 or eleven_multilingual_v2. To see the trade offs either model, see: https://elevenlabs.io/docs/models

We've excited to partner with Gladia: a new speech to text provider, providing strong multi lingual support on speech recognition side.

More details here on how to configure these, see: https://docs.heygen.com/reference/new-session

Endpoint: /v1/video/share
Reference: https://docs.heygen.com/reference/retrieve-sharable-video-url

We’ve added the Retrieve Sharable Video URL endpoint! This allows you to make a video public and retrieve a public URL for easy sharing.

• Retrieve a Translated Video action added.
• New webhook triggers for video translation events: "New Video Translate Event".
• Create WebM Avatar Video action for generating videos with transparent backgrounds.
• Added Folder ID option to video generation and translation actions.
• Added Brand Voice ID option to video translation action.
• New locale field for voice accents in video scene creation.
• Renamed some trigger and action labels for better clarity.

Learn more: HeyGen Zapier Integration