# Higgs Audio Review

> Higgs Audio review: Strong emotional/expressive open TTS from a well-funded lab - but 'Apache-2.0' only covers the repo code; V2 weights carry a 100k-MAU.

![Higgs Audio logo](https://www.versusref.com/logos/higgs-audio.png)

Strong emotional/expressive open TTS from a well-funded lab - but 'Apache-2.0' only covers the repo code; V2 weights carry a 100k-MAU community license and the newer V3 is research/non-commercial.

See pricing · Open source · facts verified Jul 20, 2026

## What we know about Higgs Audio

Higgs Audio is a text-to-speech apis platform: strong emotional/expressive open TTS from a well-funded lab - but 'Apache-2.0' only covers the repo code; V2 weights carry a 100k-MAU community license and the newer V3 is research/non-commercial. This profile tracks every Higgs Audio fact we have verified, each linked to a primary source and dated.

Higgs Audio does not publish a public per-minute rate we have been able to verify, so the price figure here stays blank until we can confirm one. We would rather show nothing than a guessed number; if you have a current Higgs Audio quote, it is the fastest way for us to close that gap.

On capabilities, Higgs Audio covers streaming audio output, instant voice cloning, emotion / style controls, and self-host / on-prem option. Each of those is verified against Higgs Audio's own docs or dashboard, not marketing copy.

In total we track 10 verified facts for Higgs Audio today, each linking the primary source it came from so you can check our work - and vendor claims we have not measured ourselves are labeled as such on the Higgs Audio fact sheet below.

## Fact sheet

### Capabilities

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Streaming audio output | ✓  Yes | Jul 20 | [source](https://github.com/boson-ai/higgs-audio) |
| Instant voice cloning | ✓  Yes | Jul 20 | [source](https://huggingface.co/bosonai/higgs-audio-v2-generation-3B-base) |
| Emotion / style controls | ✓  Yes | Jul 20 | [source](https://github.com/boson-ai/higgs-audio) |

### Compliance & trust

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Self-host / on-prem option | ✓  Yes | Jul 20 | [source](https://github.com/boson-ai/higgs-audio) |
| Model weights license | Boson Higgs Audio 2 Community License (custom | Jul 20 | [source](https://huggingface.co/bosonai/higgs-audio-v2-generation-3B-base/raw/main/LICENSE) |

### Build experience

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Official SDKs | PyTorch; HF weights; OpenAI-compatible hosted API | Jul 20 | [source](https://github.com/boson-ai/higgs-audio) |

### Commercial

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Model size (parameters) | 5.8B (V2); 4B (V3) | Jul 20 | [source](https://huggingface.co/bosonai/higgs-audio-v2-generation-3B-base) |
| Hosted API available | Yes | Jul 20 | [source](https://github.com/boson-ai/higgs-audio) |
| Project maintenance status | active | Jul 20 | [source](https://github.com/boson-ai/higgs-audio/commits/main) |
| GitHub stars | 8,300 stars | Jul 20 | [source](https://github.com/boson-ai/higgs-audio) |

Source: https://www.versusref.com/tts/tools/higgs-audio/