Higgs Audio Models by Boson AI
1 model2026Up to 8k ctx
Last refreshed 2026-06-29. Next refresh: weekly.
Details
ResearcherBoson AI
LicenseNoncommercial
Commercial useCommercial use: non-commercial
Models1
Released2026
Max context8k
Links
WebsiteAbout
Boson AI's Higgs Audio family of text-audio foundation models, spanning TTS (v3 TTS) and STT (v3 STT) variants. Designed for voice agents with zero-shot voice cloning, support for 100+ languages, and inline control over emotion, style, prosody, and sound effects.
Decision facts
- Best fit
- text to speechaudioagent workflows
- Capability starting point
- Higgs Audio v3 TTS with 8k context
- Lowest tracked input
- Not tracked
- Closest related family
- Claude 3
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
Higgs Audio v3 TTSCurrent
Use when the workload needs text to speech, 8k context, and 4B parameters.
2026-06text to speech8k context4B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Higgs Audio v3 TTS | Use when the workload needs text to speech, 8k context, and 4B parameters. | 2026-06 | text to speech8k context4B parameters | Current |
Release Timeline
1 release group2026-06
1 current
Higgs Audio v3 TTS
Currenttext to speech8k context4B parameters
Specifications(1 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| Higgs Audio v3 TTS | 2026-06 | 8k | 4B |
