Update README.md

README.md

@@ -114,16 +114,16 @@ pipeline_tag: text-to-speech
 library_name: transformers
 ---
 
-# Higgs Audio v3 TTS
+# Higgs TTS v3
 
 <div align="left" style="display: flex; justify-content: flex-start; margin-top: 10px;"> <a href="https://www.boson.ai/blog/higgs-audio-v3-tts"> <img src="https://img.shields.io/badge/💚-Boson%20Blog-228B22" style="margin-right: 5px;"> </a> </div>
 
-Higgs Audio v3 TTS is built for voice chat: it **speaks, not just reads**. It turns model responses into expressive conversational speech across **100+ languages**, with **zero-shot voice cloning** and **inline control** over emotion, style, prosody, pauses, and sound effects.
+Higgs TTS v3 is built for voice chat: it **speaks, not just reads**. It turns model responses into expressive conversational speech across **100+ languages**, with **zero-shot voice cloning** and **inline control** over emotion, style, prosody, pauses, and sound effects.
 
 > [!TIP]
-> Released for research and non-commercial use under the **Boson Higgs Audio v3 Research and Non-Commercial License**. Production, hosted APIs, or revenue-generating use requires a separate commercial license. Prohibited: voice cloning without consent, impersonation, fraud, election deception, biometric surveillance, or any unlawful use.
+> Released for research and non-commercial use under the **Boson Higgs TTS v3 Research and Non-Commercial License**. Production, hosted APIs, or revenue-generating use requires a separate commercial license. Prohibited: voice cloning without consent, impersonation, fraud, election deception, biometric surveillance, or any unlawful use.
 
-![Higgs Audio v3 TTS Architecture](./assets/model_architecture.png)
+![Higgs TTS v3 Architecture](./assets/model_architecture.png)
 
 Higgs autoregressive decoder consumes interleaved text and audio tokens. Audio is encoded by the **Higgs Tokenizer** into 8 codebooks at 25 fps, staggered via a **delay pattern**, then mapped to backbone hidden states through a **multi-codebook fused embedding**. Output codes pass through a **multi-codebook fused head**, are de-delayed, and decoded back to waveform.
 
@@ -187,7 +187,7 @@ All tags follow `<|category:value|>` syntax and can be inserted mid-utterance.
 
 ### Multilingual Voice Clone
 
-We evaluate Higgs Audio v3 TTS on public multilingual TTS suites and our internal 111-language Higgs-Multilingual set, covering both common and lower-resource languages.
+We evaluate Higgs TTS v3 on public multilingual TTS suites and our internal 111-language Higgs-Multilingual set, covering both common and lower-resource languages.
 
 WER / CER (↓, ×100) macro-averaged across each benchmark's language set. Lower is better; **bold** marks the best per row. All numbers are reproducible end-to-end with original metrics and normalization.
 
@@ -195,8 +195,8 @@ WER / CER (↓, ×100) macro-averaged across each benchmark's language set. Lowe
 <table style="width:100%;border-collapse:collapse;font-size:clamp(11px,1.4vw,13px);text-align:center">
 <thead><tr>
 <th style="padding:18px 24px;text-align:center;font-weight:600;border-bottom:2px solid #16a34a;color:#16a34a">Benchmark</th>
-<th style="padding:18px 24px;text-align:center;font-weight:500;white-space:nowrap;border-bottom:2px solid #16a34a;color:#16a34a;font-size:14px">Higgs Audio v2</th>
-<th style="padding:18px 24px;text-align:center;font-weight:500;white-space:nowrap;border-bottom:2px solid #16a34a;color:#16a34a;font-size:14px">Higgs Audio v3</th>
+<th style="padding:18px 24px;text-align:center;font-weight:500;white-space:nowrap;border-bottom:2px solid #16a34a;color:#16a34a;font-size:14px">Higgs TTS v2</th>
+<th style="padding:18px 24px;text-align:center;font-weight:500;white-space:nowrap;border-bottom:2px solid #16a34a;color:#16a34a;font-size:14px">Higgs TTS v3</th>
 <th style="padding:18px 24px;text-align:center;font-weight:500;white-space:nowrap;border-bottom:2px solid #16a34a;color:#16a34a;font-size:14px">Fish Audio S2 Pro</th>
 <th style="padding:18px 24px;text-align:center;font-weight:500;white-space:nowrap;border-bottom:2px solid #16a34a;color:#16a34a;font-size:14px">Qwen3-TTS-1.7B</th>
 <th style="padding:18px 24px;text-align:center;font-weight:500;white-space:nowrap;border-bottom:2px solid #16a34a;color:#16a34a;font-size:14px">VibeVoice-7B</th>
@@ -286,7 +286,7 @@ Win-rate (↑) per category — judge preference vs the BASELINE row; **bold** m
 </tr></thead>
 <tbody>
 <tr>
-<td style="padding:16px 24px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">Higgs Audio v3</td>
+<td style="padding:16px 24px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">Higgs TTS v3</td>
 <td style="padding:16px 24px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-weight:600">53.65%</td>
 <td style="padding:16px 24px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15)">53.75%</td>
 <td style="padding:16px 24px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-weight:600">48.75%</td>
@@ -372,10 +372,10 @@ uv pip install -v -e .
 
 ```bash
 export HF_TOKEN=hf_xxxxxxxxxxxxxxxx
-hf download bosonai/higgs-audio-v3-tts-4b
+hf download bosonai/higgs-tts-v3-4b
 
 sgl-omni serve \
-  --model-path bosonai/higgs-audio-v3-tts-4b \
+  --model-path bosonai/higgs-tts-v3-4b \
   --port 8000
 ```
 
@@ -515,9 +515,9 @@ To reproduce the results, follow the instructions in [this script](https://githu
 You can also serve these weights with [**vLLM-Omni**](https://github.com/vllm-project/vllm-omni), which exposes the same OpenAI-compatible `/v1/audio/speech` API with zero-shot voice cloning.
 
 ```bash
-hf download bosonai/higgs-audio-v3-tts-4b
+hf download bosonai/higgs-tts-v3-4b
 
-vllm-omni serve bosonai/higgs-audio-v3-tts-4b \
+vllm-omni serve bosonai/higgs-tts-v3-4b \
   --host 0.0.0.0 --port 8095 \
   --trust-remote-code --omni
 ```
@@ -525,11 +525,11 @@ vllm-omni serve bosonai/higgs-audio-v3-tts-4b \
 ```bash
 curl -X POST http://localhost:8095/v1/audio/speech \
   -H "Content-Type: application/json" \
-  -d '{"model": "bosonai/higgs-audio-v3-tts-4b", "input": "Hello, how are you?"}' \
+  -d '{"model": "bosonai/higgs-tts-v3-4b", "input": "Hello, how are you?"}' \
   --output output.wav
 ```
 
-Plain-text TTS, voice-clone, and benchmark recipes are in the [vLLM-Omni Higgs Audio v3 recipe](https://github.com/vllm-project/vllm-omni/blob/main/recipes/BosonAI/Higgs-Audio-V3-TTS.md).
+Plain-text TTS, voice-clone, and benchmark recipes are in the [vLLM-Omni Higgs TTS v3 recipe](https://github.com/vllm-project/vllm-omni/blob/main/recipes/BosonAI/Higgs-Audio-V3-TTS.md).
 
 ### API Usage
 
@@ -539,13 +539,13 @@ For zero-ops deployment, use the [**Boson AI API**](https://docs.boson.ai/models
 
 ```bibtex
 @misc{bosonai_higgs_audio_tts_v3_2026,
-  title  = {Higgs Audio v3 TTS: Conversational Speech for Voice AI from Boson AI},
+  title  = {Higgs TTS v3: Conversational Speech for Voice AI from Boson AI},
   author = {Boson AI},
   year   = {2026},
-  howpublished = {https://huggingface.co/bosonai/higgs-audio-v3-tts-4b},
+  howpublished = {https://huggingface.co/bosonai/higgs-tts-v3-4b},
 }
 ```
 
 ## License
 
-Boson Higgs Audio v3 Research and Non-Commercial License — see [LICENSE](./LICENSE).
+Boson Higgs TTS v3 Research and Non-Commercial License — see [LICENSE](./LICENSE).