HeyGen Voice Turbo tops the TTS leaderboard and is free on the API until November 30
HeyGen made Voice Turbo, the fast mode of its in-house voice model, free to use through its API until November 30, 2026, including voices you clone from one recording. HeyGen says Turbo ranks first on the Artificial Analysis text-to-speech leaderboard, just ahead of its full model.
What it does
Create an API key, call Text to Speech with the Turbo model and get back a link to a WAV file. It works with HeyGen's public voices and with instant voices cloned from a single recording, which are also free to create during the preview.
Results and limits
The leaderboard comes from blind listening tests where every model reads the same eight cloned voices; HeyGen lists Turbo first and HeyGen Voice second, ahead of Qwen-Audio-3.1, Eleven v4 Turbo and Eleven v4.
Worth knowing
Free use is best effort: when capacity is full you get a 429 error and have to retry. Professional voice clones need the paid heygen-voice-1 model. You can also use it inside ComfyUI through the HeyGen Voice 1.0 nodes.