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

[Qwen3TTS] [TTS] [Feat] Refactor voice cache manager (#2108)

Browse Source 
Signed-off-by: JuanPZuluaga <juanz9312@gmal.com>
Signed-off-by: yiliu30 <yi4.liu@intel.com>
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Signed-off-by: Binh Tang <tangbinhna@gmail.com>
Signed-off-by: Binh Tang <binht@netflix.com>
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
Signed-off-by: Rein Yang <ruiruyang2@gmail.com>
Signed-off-by: CHEN <116010019@link.cuhk.edu.cn>
Signed-off-by: vraiti <vraiti@redhat.com>
Signed-off-by: Songrui625 <songrui625@gmail.com>
Signed-off-by: Lidang Jiang <lidangjiang@gmail.com>
Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>
Signed-off-by: Alex Brooks <albrooks@redhat.com>
Co-authored-by: JuanPZuluaga <juanz9312@gmal.com>
Co-authored-by: Yi Liu <yi4.liu@intel.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Canlin Guo <canlinguosdu@gmail.com>
Co-authored-by: Binh Tang <tangbinhna@gmail.com>
Co-authored-by: Binh Tang <binht@netflix.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
Co-authored-by: rein yang <73573651+R2-Y@users.noreply.github.com>
Co-authored-by: zhumingjue138 <zhumingjue@huawei.com>
Co-authored-by: ChenWenjing <54166744+Shirley125@users.noreply.github.com>
Co-authored-by: vraiti <vraiti@redhat.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: Sy03 <1370724210@qq.com>
Co-authored-by: chickeyton <ngton2014@gmail.com>
Co-authored-by: Jerry Song <46962917+Songrui625@users.noreply.github.com>
Co-authored-by: Lidang Jiang <119769478+Lidang-Jiang@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Alex Brooks <albrooks@redhat.com>
Co-authored-by: linyueqian <linyueqian@outlook.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
This commit is contained in:
+11
Juan Pablo ZuluagaJuanPZuluagaYi LiuHongsheng LiuCanlin GuoBinh TangBinh TangDidan Dengrein yangzhumingjue138ChenWenjingvraiti汪志鹏Sy03chickeytonJerry SongLidang JiangClaude Opus 4.6Alex BrookslinyueqianYueqian Lin
 authored and GitHub committed 2026-04-03 16:51:58 -04:00
1 parent 0e83ebe1d4
commit f50c5a413f
11 files changed
+442 -614
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/user_guide/examples/online_serving/qwen3_tts.md
+22 -12
View File
@@ -159,7 +159,7 @@ curl -X POST http://localhost:8091/v1/audio/speech \
-H "Content-Type: application/json" \
-d '{
"input": "Hello, how are you?",
"speaker": "vivian",
"voice": "vivian",
"language": "English"
}' --output output.wav
@@ -168,7 +168,7 @@ curl -X POST http://localhost:8091/v1/audio/speech \
-H "Content-Type: application/json" \
-d '{
"input": "I am so excited!",
"speaker": "vivian",
"voice": "vivian",
"instructions": "Speak with great enthusiasm"
}' --output excited.wav
@@ -185,7 +185,7 @@ client = OpenAI(base_url="http://localhost:8091/v1", api_key="none")
response = client.audio.speech.create(
model="Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice",
speaker="vivian",
voice="vivian",
input="Hello, how are you?",
)
@@ -201,7 +201,7 @@ response = httpx.post(
"http://localhost:8091/v1/audio/speech",
json={
"input": "Hello, how are you?",
"speaker": "vivian",
"voice": "vivian",
"language": "English",
},
timeout=300.0,
@@ -237,12 +237,16 @@ List all available voices/speakers from the loaded model, including both built-i
"consent": "user_consent_id",
"created_at": 1738660000,
"file_size": 1024000,
"mime_type": "audio/wav"
"mime_type": "audio/wav",
"ref_text": "The exact transcript of the audio sample.",
"speaker_description": "warm narrator"
}
]
}
```
Fields `ref_text` and `speaker_description` are omitted per-entry when not provided at upload time.
#### POST /v1/audio/voices
Upload a new voice sample for voice cloning in Base task TTS requests.
@@ -252,6 +256,7 @@ Upload a new voice sample for voice cloning in Base task TTS requests.
- `consent` (required): Consent recording ID
- `name` (required): Name for the new voice
- `ref_text` (optional): Transcript of the audio. Enables in-context voice cloning (higher quality).
- `speaker_description` (optional): Free-form description of the voice (e.g. "warm narrator", "energetic presenter"). Stored as metadata.
**Response Example:**
```json
@@ -262,18 +267,23 @@ Upload a new voice sample for voice cloning in Base task TTS requests.
"consent": "user_consent_id",
"created_at": 1738660000,
"mime_type": "audio/wav",
"file_size": 1024000
"file_size": 1024000,
"ref_text": "The exact transcript of the audio sample.",
"speaker_description": "warm narrator"
}
}
```
Fields `ref_text` and `speaker_description` are omitted when not provided at upload time.
**Usage Example:**
```bash
curl -X POST http://localhost:8000/v1/audio/voices \
curl -X POST http://localhost:8091/v1/audio/voices \
-F "audio_sample=@/path/to/voice_sample.wav" \
-F "consent=user_consent_id" \
-F "name=custom_voice_1" \
-F "ref_text=The exact transcript of the audio sample."
-F "ref_text=The exact transcript of the audio sample." \
-F "speaker_description=warm narrator"
```
### Endpoint
@@ -290,7 +300,7 @@ This endpoint follows the [OpenAI Audio Speech API](https://platform.openai.com/
```json
{
"input": "Text to synthesize",
"speaker": "vivian",
"voice": "vivian",
"response_format": "wav",
"task_type": "CustomVoice",
"language": "Auto",
@@ -310,7 +320,7 @@ Returns binary audio data with appropriate `Content-Type` header (e.g., `audio/w
### Voice and language (summary)
- **Speaker**: Use the `speaker` request field to select the speaker (e.g., `vivian`, `ryan`, `aiden`). List available speakers with `GET /v1/audio/voices`.
- **Speaker**: Use the `voice` request field to select the speaker (e.g., `vivian`, `ryan`, `aiden`). List available speakers with `GET /v1/audio/voices`.
- **Language**: Use the `language` field for the codec language tag (`Auto`, `Chinese`, `English`, etc.). Default is `Auto` for automatic detection.
- **CustomVoice**: Requires a valid `voice` from the model’s speaker set. **VoiceDesign**: Use `instructions` to describe the voice. **Base**: Use `ref_audio` and `ref_text` for voice cloning.
@@ -322,7 +332,7 @@ Returns binary audio data with appropriate `Content-Type` header (e.g., `audio/w
| ----------------- | ------ | -------------- | ----------------------------------------------------------- |
| `input` | string | **required** | Text to synthesize |
| `model` | string | server's model | Model to use (optional, should match server if specified) |
| `speaker` | string | "vivian" | Speaker name (e.g., vivian, ryan, aiden) |
| `voice` | string | "vivian" | Speaker name (e.g., vivian, ryan, aiden) |
| `response_format` | string | "wav" | Audio format: wav, mp3, flac, pcm, aac, opus |
| `speed` | float | 1.0 | Playback speed (0.25-4.0, not supported with `stream=true`) |
@@ -357,7 +367,7 @@ curl -X POST http://localhost:8091/v1/audio/speech \
-H "Content-Type: application/json" \
-d '{
"input": "Hello, how are you?",
"speaker": "vivian",
"voice": "vivian",
"language": "English",
"stream": true,
"response_format": "pcm"