anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Model] Add Breeze-TTS-2 two-stage AR TTS support (talker + codec, streaming) (#7084)

Browse Source 
Signed-off-by: noname <liuzhiwei08@kuaishou.com>
Signed-off-by: noname <133508552+lzwnoname@users.noreply.github.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: noname <liuzhiwei08@kuaishou.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
This commit is contained in:
nonamenonameYueqian Lin
 authored and GitHub committed 2026-09-14 09:55:53 -07:00
1 parent e0c4f97f32
commit ea1a416a17
46 files changed
+6067 -4
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/models/supported_models.md
+1
View File
@@ -71,6 +71,7 @@ th {
| `AuKForConditionalGeneration` | AuK / AuK-Flash (instruction-driven speech generation and editing) | `tencent/AuK`, `tencent/AuK-Flash` (with `Qwen/Qwen2.5-Omni-3B`; assemble with `tools/prepare_auk_checkpoint.py`) | ✅︎ | | | | [Repository](https://github.com/vllm-project/vllm-omni/blob/main/recipes/Tencent/AuK-H100.md) |
| `OmniVoiceModel` | OmniVoice | `k2-fsa/OmniVoice` | ✅︎ | | | ✅︎ | — |
| `VoxCPM2TalkerForConditionalGeneration` | VoxCPM2 | `openbmb/VoxCPM2` | ✅︎ | | | ✅︎ | — |
| `BreezeForConditionalGeneration` | Breeze-TTS-2 (TTS, voice clone, voice direction) | `BreezeBlue/Breeze-TTS-2` | ✅︎ | | | | [Repository](https://github.com/vllm-project/vllm-omni/blob/main/recipes/BreezeBlue/Breeze-TTS-2.md) |
| `DotsTTSForConditionalGeneration` | dots.tts | `dots-studio/dots.tts-soar` | ✅︎ | | | | — |
| `MammothModa2ForConditionalGeneration` | MammothModa2-Preview | `bytedance-research/MammothModa2-Preview` | ✅︎ | ✅︎ | | | — |
| `MammothModa2ForConditionalGeneration` | MammothModa2-Dev (AR-only image understanding) | `bytedance-research/MammothModa2-Dev` | ✅︎ | | | | — |
docs/serving/speech_api.md
+7 -1
View File
@@ -7,7 +7,7 @@ vLLM-Omni provides an OpenAI-compatible API for text-to-speech (TTS) generation.
- **Voxtral TTS** (`mistralai/Voxtral-4B-TTS-2603`) -- AR + FlowMatching TTS with preset voices. Output: 24 kHz.
- **CosyVoice3** (`FunAudioLLM/Fun-CosyVoice3-0.5B-2512`) -- 2-stage talker + flow-matching code2wav. Voice cloning via `ref_audio` + `ref_text` (no presets). Output: 24 kHz.
See the [Supported Models](#supported-models) section below for the full list, including OmniVoice, VoxCPM2, and MOSS-TTS-Nano.
See the [Supported Models](#supported-models) section below for the full list, including OmniVoice, VoxCPM2, MOSS-TTS-Nano, and Breeze-TTS-2.
!!! tip "Deployment recipes"
TTS deployment recipes are published at
@@ -783,6 +783,12 @@ hidden-state dtype before the output projection. Consequently, a float32 stage c
| ------- | ------------- |
| `OpenMOSS-Team/MOSS-TTS-Nano` | Voice cloning only. Requires `ref_audio` (or an uploaded `voice`); no built-in voice presets. `ref_text` is accepted but ignored — upstream's `voice_clone` mode does not consume a transcript. |
### Breeze-TTS-2
| Model | Description |
| ------- | ------------- |
| `BreezeBlue/Breeze-TTS-2` | Two-stage AR TTS (T5Gemma2 + Qwen3 talker with a depth decoder, bundled Qwen3-TTS codec) at 24 kHz. Four modes are selected from the request fields: plain (`input` + speaker tag `voice`, `S0`..`S9`), voice design (`instructions`), voice clone (`ref_audio` + `ref_text`, exactly one clip), and voice direction (reference + `instructions`). Greedy decoding only: `sample_rate` must be `24000`, `speed` must be `1.0`, and `guidance_scale`/`cfg_scale` other than `1.0`, `negative_prompt`, `temperature`/`top_p`/`top_k` overrides, `language`, and `speaker_embedding` are rejected. Streaming returns PCM `speech.audio.delta` events. See [`recipes/BreezeBlue/Breeze-TTS-2.md`](https://github.com/vllm-project/vllm-omni/blob/main/recipes/BreezeBlue/Breeze-TTS-2.md). |
## Error Responses
### 400 Bad Request