The #1-ranked text-to-speech model on Artificial Analysis now costs nothing to use through November 30. Bring an API key, pick a voice, and start shipping speech today.
What is HeyGen Voice Turbo?
HeyGen Voice is the in-house voice model behind every HeyGen video. Turbo is its fast mode: the same voices with a shorter generation step, so audio comes back sooner and costs less to run. Faster didn't mean worse: in blind listening tests, Turbo ranks just ahead of the full model.
It's built to sound like you: natural, authentic delivery instead of a flat studio read. Turbo works with HeyGen's public voices and with any instant voice you clone from a single recording.
#1 and #2 on the leaderboard
HeyGen Voice Turbo ranks first and HeyGen Voice second on the Artificial Analysis text-to-speech leaderboard, ahead of Qwen-Audio-3.1, Eleven v4 Turbo and Eleven v4. Every model reads the same eight cloned voices (four US, four UK), so the comparison is about the model, not the voice. The rankings come from blind listening tests: people hear two clips and pick the one that sounds better.
Start in one request
Create a key on the API keys page, then call Text to Speech with the free model. You get back a link to a WAV file.
What "free" means
- Free through November 30, 2026. We'll give advance notice before anything changes.
- Best effort: no uptime or latency guarantee. When free capacity is full, requests return
429, so retry later. - Voices: public voices and your instant voices. Professional voice clones need
heygen-voice-1.
Ready for production?
Switch the model name. Nothing else in your request changes.
Questions
Do I need a credit card?
No. Create a HeyGen account and an API key, and the free model works right away.
Can I use my own voice?
Yes. Clone an instant voice from one recording. Creating instant voices is free during the preview.
