Model reference · open weights
higgs-tts-2 is an open-weight audio or speech model from bosonai, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Higgs TTS 2: Redefining Expressiveness in Audio Generation Check our open-source repository https://github.com/boson-ai/higgs-audio for more details! Rename note: Higgs Audio V2 and Higgs Audio V2 Generation have been renamed to Higgs TTS 2. We are open-sourcing Higgs TTS 2, a powerful audio foundation model pretrained on over 10 million hours of audio data and a diverse set of text data. Despite having no post-training or fine-tuning, Higgs TTS 2 excels in expressive audio generation, thanks to its deep language and acoustic understanding. On EmergentTTS-Eval, the model achieves win rates of 75.7% and 55.7% over "gpt-4o-mini-tts" on the "Emotions" and "Questions" categories, respectively. It also obtains state-of-the-art performance on traditional TTS benchmarks like Seed-TTS Eval and Emotional Speech Dataset (ESD). Moreover, the model demonstrates capabilities rarely seen in previous systems, including automatic prosody adaptation during narration, zero-shot generation of natural multi-speaker dialogues in multiple languages, melodic humming with the cloned voice, and simultaneous generation of speech and background music. Here's the demo video that shows some of its emergent capabilities (remember to unmute): Your browser does not support the video tag. Here's another demo video that show-cases the model's multilingual capability and how it enabled live translation (remember to unmute): Your browser does not support the video tag. Technical Details Higgs TTS 2 adopts the "generation variant" depicted in the architecture figure above. Its strong performance is driven by three key technical innovations: - We developed an automated annotation pipeline that leverages multiple ASR models, sound event classification models, and our in-house audio understanding model. Using this pipeline, we cleaned and annotated 10 million hours audio data, which we refer to as AudioVerse. The in-house understanding model is finetuned on top of Higgs Audio v1 Understanding, which adopts the "understanding variant" shown in the architecture figure. - We trained a unified audio tokenizer from scratch that captures both semantic and acoustic features. - We proposed the DualFFN archite
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | bosonai |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 5.8B |
| Variants | 1 |
| Runs with | transformers |
| Released | 2025-07-01 |
| Popularity | 541k downloads / month |
| Likes | 693 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| higgs-tts-2-3b-base | 5.8B | BF16 | ~13.3 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys higgs-tts-2 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (higgs-tts-2 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="higgs-tts-2" -F file=@audio.mp3
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗