HeyGen Voice is free in the API: what a talking video costs
HeyGen Voice launched Oct 9 as free in the platform and API. A voice model is one part of a talking video; see Sume's per-second render prices by tier.
A free voice model does not make a talking-avatar video free. HeyGen announced HeyGen Voice on October 9, 2026 as free within its platform and API, but the voice is only the audio layer. The face, lip movement and render are still what you pay for. On Sume the render is billed per second by quality tier: $0.184 on standard, $0.245 on plus and $0.55 on max, with no product image.
What did HeyGen actually announce?
HeyGen's release says HeyGen Voice debuted at number one on an Artificial Analysis leaderboard, is free within the HeyGen platform and API, and has an optional Professional Voice Clone add-on at $99 a month, trained with explicit consent on 30 minutes to three hours of the owner's speech.
HeyGen's developer docs describe the API side: instant voices are free during a preview period, and professional speech generation is listed at 0.6 API credits per generated minute. Those are HeyGen's terms as of the date read; check them before you plan around them.
What does a voice model not cover?
A talking video needs a face that is consistent across clips, a scene, and lip movement that matches the audio. Audio generation answers only the last question. When you compare tools, price the whole clip, not the voice line item.
- Voice: who speaks and how it sounds.
- Presenter: a reusable face you can name and call again.
- Render: the seconds of finished video you are billed for.
How does Sume bill a scripted avatar video?
You create an avatar once (a flat $0.95 per avatar, from a prompt, a profile or a photo) and then call POST /v1/avatar-1.0/talking-video with its avatar_handle and a script. Sume accepts scripts and multi-scene plans whose estimated duration is 4 to 60 seconds. Quality is standard, plus (the default) or max, and the output is 720p.
Adding a product_image raises the per-second rate slightly: $0.194 standard, $0.258 plus and $0.58 max. The table shows the no-product cost for common lengths.
| Length | Standard ($0.184/s) | Plus ($0.245/s) | Max ($0.55/s) |
|---|---|---|---|
| 10 s | $1.84 | $2.45 | $5.50 |
| 30 s | $5.52 | $7.35 | $16.50 |
| 60 s | $11.04 | $14.70 | $33.00 |
How do you keep the spend predictable?
Create an avatar video preview first. It renders first-frame stills for the composition without starting the full talking-video render, and you call generate-video on the preview id once you approve it. Use the same avatar_handle across scripts so the presenter stays the same without a new creation charge.
If you need your own cloned voice, Sume's avatar route is script-driven; see the linked comparison on what Sume does and does not offer there before choosing.
Sources
Related posts
More in Sume Avatar 1.0
- Is my Sume avatar ready? Check resource_status and preview_video_url
Read a Sume Avatar 1.0 resource before your first talking video: resource_status, preview_image_url, nullable preview_video_url, voice.status, handle filter.
- UGC avatar scene prompt: why dim, glary lighting words are kept
Sume's first-frame step copies lighting words from your scene prompt as written, so ordinary light like TV glow or a side window stays. How to write it.
- Introducing Sume Avatar 1.0
Sume Avatar 1.0 is a multi-agent orchestration system as a single avatar model.
- Avatar Face Swap API (Beta): apply an avatar face to a video
Avatar Face Swap 1.0 is a Beta Sume endpoint that applies a ready avatar's face to a short public source video. Required fields, limits, and polling.
Written by Sume