HeyGen API Feature Requests

Hey VEO 3 is killing in the market and we want to have that in HeyGen too

Hi HeyGen team! 👋 I've been working extensively with the Avatar IV API and would love to see two specific enhancements that would greatly improve the developer experience and functionality: 🎵 External Audio File Support (Like Talking Photo API) Current State: The Talking Photo API already supports external audio files beautifully with this structure: json{ "voice": { "type": "audio", "audio_url": " https://example.com/audio.mp3 " } } Request: Please add the same external audio file support to Avatar IV API. Currently, when trying to use audio with Avatar IV, the API still requires a script field even when providing audio configuration, which seems inconsistent with the Talking Photo behavior. Use Cases: Using pre-recorded professional voiceovers Multi-language content with native speakers Custom audio processing/effects Consistent audio branding across videos Suggested Implementation: Allow Avatar IV to accept the same audio voice configuration as Talking Photo: json{ "voice": { "type": "audio", "audio_url": " https://example.com/audio.mp3 " // OR "audio_asset_id": "your_uploaded_asset_id" } } 🌍 Enhanced ElevenLabs Voice Configuration Current State: ElevenLabs voices in Avatar IV seem to have limited configuration options compared to what ElevenLabs API offers natively. Request: Please add support for additional ElevenLabs parameters: Language/Model Selection: Allow specifying ElevenLabs models (e.g., eleven_multilingual_v2, eleven_turbo_v2) Language Code: Enable language-specific optimization for non-English content Voice Settings: Expose stability, similarity_boost, and style parameters Suggested API Structure: json{ "voice": { "type": "text", "voice_id": "elevenlabs_voice_id", "provider": "elevenlabs", "language": "es", "model": "eleven_multilingual_v2", "voice_settings": { "stability": 0.75, "similarity_boost": 0.75, "style": 0.5 } } } Benefits: Better multilingual support Improved voice quality control Consistency with ElevenLabs best practices More granular voice customization Why These Features Matter Both of these enhancements would: ✅ Improve API consistency across HeyGen products ✅ Enable more professional use cases ✅ Better serve international/multilingual developers ✅ Align with industry standards (ElevenLabs native capabilities) Community Impact I believe these features would benefit many developers in the community who are building: International content platforms Professional video production tools Educational applications Marketing automation systems Would love to hear the team's thoughts on this! Is this something that could be considered for a future release? Thanks for all the amazing work on HeyGen! 🚀

For now we're only able to go from a uploaded image to Avatar IV through the API. We would like to use a look of a digital twin for this, with Avatar IV and the API.

I need to input a text with an avatar id and may be with an emotion like(happy, sad...etc) and return an audio with mp3 extension.

Avatar v2 supports audio file input. Please also support it in Avatar IV.

You urgently need to make the Brand Glossary available for API use... it's clearly a tool meant to be used in mass production, but there's no way to automate it with an API... only by using the website manually.

In Studio, when creating a template, you're able to select the Avatar IV option for an avatar together with an API tag. But when running the template from the API, the video gets stuck at around 10%-13%. Heygen support says it's not a bug, but just not supported. We would love to have this functionality!

• Splitting tracks shortcut • Moving tracks up and down feature • Track deleting option with single click • Zooming in and out Shortcut • Shifting of clips by dragging up/down tracks • Overlapping Dialogue Support • overlapping dialogue, such as crowds or multiple speakers talking simultaneously. • Slow or Unresponsive Generation • At times, the video generation process is very slow or gets stuck entirely. This impacts delivery timelines and project planning. • Export Options – Separate Audio Tracks per Speaker • Currently, the export is limited to a single video file. We would greatly appreciate the ability to export separate audio tracks for each speaker, which is essential for post-production and dubbing.