Data as of October 14, 2026 · How the score is built
N/A contextHeyGen model card
HeyGen Voice
Decision readingHeyGen Voice is tracked, but not publicly ranked yet. Published speech or voice results from HeyGen Voice evaluation appear below. They do not produce a weighted text-model score.
HeyGen Voice will be repriced, updated or retired. Get each notice with its source and date. Follow model changes
Voice benchmark evidence
HeyGen Voice evaluation is an owner-defined voice evaluation. Its result stays separate from BenchLM's weighted text-model ranking.
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not publishedHeyGen model documentation
- Context window
- N/A
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not disclosed by the provider
- Availability
- HeyGen published its research report on October 14, 2026 and links a platform trial. The model combines a script, voice reference, target image, and scene descriptions to produce 44.1 kHz audio. Voice-clone and full-clone are modes of the same model; a separate avatar model renders the video. The report does not identify a versioned public API model ID. The report date is not a verified first-availability date.
- Cloud regions
- Not tracked yet
- Lifecycle
- Tracked
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordHeyGen model documentation
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track HeyGen Voice, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
HeyGen Voice is a proprietary model with a N/A context window. No explicit reasoning mode is documented in this profile.
HeyGen published its research report on October 14, 2026 and links a platform trial. The model combines a script, voice reference, target image, and scene descriptions to produce 44.1 kHz audio. Voice-clone and full-clone are modes of the same model; a separate avatar model renders the video. The report does not identify a versioned public API model ID. The report date is not a verified first-availability date.
HeyGen Voice generates scene-aware cloned speech for talking videos. Its listening studies stay separate from weighted text-model scores.
Speech or voice evidence appears above; text-model benchmark coverage remains empty.
Last updated October 14, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does HeyGen Voice perform overall in AI benchmarks?
HeyGen Voice has published speech or voice results in HeyGen Voice evaluation. Those results remain separate from the weighted text-model ranking, so this profile does not assign a BenchLM score or overall rank. Use the linked evaluation's metric and run conditions to compare speech systems.
Does HeyGen Voice have full benchmark coverage on BenchLM?
No. HeyGen Voice's speech or voice results appear in HeyGen Voice evaluation, but it has no published text-model benchmark rows. The voice evaluation does not fill the text-model coverage slots or produce an overall rank. Missing text coverage is not treated as a zero score.
What is the context window size of HeyGen Voice?
HeyGen Voice has a reported context window of N/A in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.