# Is HeyGen Voice Turbo SOTA?

Pending benchmarks. Announced Oct 14, 2026; no independent results yet.

As of Nov 22, 2026, HeyGen Voice Turbo is pending benchmarks on isitsota: announced Oct 14, 2026, with no independent results on the boards we track yet.

The faster, lower-latency mode of HeyGen Voice, HeyGen's text-to-speech model. On the HeyGen API it is the heygen-voice-1-turbo model for public voices and instant clones; professional clones use the default heygen-voice-1. 39 languages, up to 5,000 characters per request. Also on OpenRouter and fal, with a free Turbo endpoint until November 30, 2026. Not an LLM.

Canonical: https://isitsota.com/m/heygen-voice-turbo
Last updated: 2026-11-03
Tracking since: 2026-11-03

## Announced facts

| Fact | Value |
| --- | --- |
| Lab | HeyGen |
| Announced | Oct 14, 2026 |
| API | Live (`heygen-voice-1-turbo`) |
| Open weights | Unknown · Not stated |
| Task | Text to speech |
| Relation | A mode of HeyGen Voice (heygen-voice-1, launched Oct 9, 2026), which isitsota does not track separately |
| Voices | HeyGen public voices and HeyGen Voice 1 instant clones; not professional clones (HeyGen docs). OpenRouter ships 10 default voices |
| Languages | 39 (HeyGen docs language list) |
| Request size | Up to 5,000 characters |
| Free tier | heygen-voice-1-turbo-free, free until November 30, 2026 (HeyGen docs) |
| API access | HeyGen API (/v3/models/audio/tts and /tts/stream), OpenRouter (heygen/heygen-voice-1-turbo), fal |
| Dating | Oct 14: OpenRouter's HeyGen Voice launch post named the Turbo mode and HeyGen reposted it; HeyGen's own Turbo post followed Oct 21 |

Tags marked unsure are not stated on the lab's own pages.

## What would let us call it

Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.

- [x] Publicly announced with a source
- [x] Usable by the public (API or weights)
- [ ] Listed on an independent board we track
- [ ] Enough results for a rank in a category
- [ ] Holds across two snapshots (crowns only)

## What the lab claims

Self-reported. Shown for context; not used in any verdict.

- Lab claim: #1 on the Artificial Analysis text-to-speech leaderboard as of Oct 21, 2026, with HeyGen Voice #2.
- Lab claim: Turbo is the faster, cheaper mode of the voice model behind every HeyGen video.

## Sources

- PRESS: [OpenRouter HeyGen Voice launch post on X](https://x.com/OpenRouter/status/2110392197946482934) (2026-10-14)
- LAB: [HeyGen Voice Turbo post on X](https://x.com/HeyGen/status/2112960858624078265) (2026-10-21)
- PRESS: [fal HeyGen Video and Voice post on X](https://x.com/fal/status/2113013413592842486) (2026-10-21)
- LAB: [HeyGen Text to Speech API docs](https://developers.heygen.com/docs/voices/heygen-voice-speech)
- LAB: [HeyGen API changelog](https://developers.heygen.com/changelog)
- PRESS: [HeyGen Voice Turbo on OpenRouter](https://openrouter.ai/heygen/heygen-voice-1-turbo)

Tracking continues until an independent board lists it.

## Related

- Lab: [HeyGen](https://isitsota.com/labs/heygen.md)
- All pending releases: https://isitsota.com/releases.md
- JSON: https://api.isitsota.com/v1/models/heygen-voice-turbo
