HeyGen Voice Models by HeyGen
HeyGenProprietary
HeyGen releases · 3 in the last 12 months · this family litChangelog →
2 models2026From $4.00/1M input
Last refreshed 2026-10-22. Next refresh: weekly.
About
HeyGen's text-to-speech models (Voice, Voice Turbo).
Decision facts
- Best fit
- text to speech
- Capability starting point
- HeyGen Voice Turbo
- Lowest tracked input
- HeyGen Voice Turbo · $4.00/1M · fal API
- Closest related family
- HeyGen Video
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
2 in view
HeyGen Voice TurboCurrent
Use when the workload needs text to speech and audio.
2026-10text to speechaudio
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| HeyGen Voice Turbo | Use when the workload needs text to speech and audio. | 2026-10 | text to speechaudio | Current |
| HeyGen Voice | Use when the workload needs text to speech and audio. | 2026-10 | text to speechaudio | Current |
Release Timeline
1 release group2026-10
2 current
HeyGen Voice
Currenttext to speechaudio
HeyGen Voice Turbo
Currenttext to speechaudio
Specifications(2 models)
| Model | Released |
|---|---|
| HeyGen Voice Turbo | 2026-10 |
| HeyGen Voice | 2026-10 |
Available From(3 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| HeyGen Voice Turbo | fal API | $4 | — | Serverless |
| HeyGen Voice | fal API | $30 | — | Serverless |
| HeyGen Voice | HeyGen API | $30 | — | Serverless |