Ming-3.0-TTS#
Ming-3.0-tts-tiny and Ming-3.0-tts-0.5B synthesize speech from text and can clone one reference voice. A flow-matching head predicts one continuous 64-dimensional latent per step, a CAM++ speaker embedding conditions the prompt, and an AudioVAE decoder turns the latents into a 44.1 kHz waveform.
Tiny uses a Ling V3 mixture-of-experts backbone. Leaving out ref_audio writes a zero speaker embedding. ref_text is accepted and does not change that embedding. The checkpoint temperature is 1.5. Speech can stop when the stop head exceeds 0.5, and not before 13 steps. max_new_tokens is clamped to 250.
The 0.5B checkpoint uses a dense Qwen2.5-0.5B backbone. Leaving out ref_audio inserts no speaker token. ref_text is the transcript of the reference recording, and the server encodes that recording into prompt latents only when ref_text is present. The checkpoint temperature is 0. Speech can stop when the stop head exceeds 0.5, and not before 5 steps. max_new_tokens is clamped to 1000.
Installation and Startup#
Install SGLang-Omni by following Installation.
Startup uses one GPU. Preprocessing runs on the CPU. The backbone and the VAE decoder share that GPU. The two checkpoints differ only by the model path.
sgl-omni serve --model-path inclusionAI/Ming-3.0-tts-tiny
sgl-omni serve --model-path inclusionAI/Ming-3.0-tts-0.5B
The speech endpoint is POST /v1/audio/speech. The body is one complete waveform. stream=true still waits until that waveform is finished, then returns it as a single PCM body. The requests below are the same for both servers. Set model to the checkpoint id used at startup. The examples use inclusionAI/Ming-3.0-tts-tiny.
Zero-shot speech#
Leave out ref_audio. seed fixes the flow-matching noise. response_format accepts wav, mp3, flac, and pcm. The default is wav.
Use curl
curl -X POST http://127.0.0.1:8000/v1/audio/speech \
-H "Content-Type: application/json" \
-d '{
"model": "inclusionAI/Ming-3.0-tts-tiny",
"input": "Get the trust fund to the bank early.",
"response_format": "wav",
"seed": 123
}' \
--output speech.wav
Use Python
import requests
response = requests.post(
"http://127.0.0.1:8000/v1/audio/speech",
json={
"model": "inclusionAI/Ming-3.0-tts-tiny",
"input": "Get the trust fund to the bank early.",
"response_format": "wav",
"seed": 123,
},
timeout=180,
)
response.raise_for_status()
open("speech.wav", "wb").write(response.content)
The same request synthesizes Chinese. An empty input is HTTP 400.
curl -X POST http://127.0.0.1:8000/v1/audio/speech \
-H "Content-Type: application/json" \
-d '{
"model": "inclusionAI/Ming-3.0-tts-tiny",
"input": "明天早上八点在会议室见。",
"response_format": "wav",
"seed": 123
}' \
--output speech-zh.wav
temperature overrides the checkpoint default. max_new_tokens limits the latent steps and is clamped to that checkpoint’s maximum. Speech can stop earlier, when the stop head exceeds 0.5.
curl -X POST http://127.0.0.1:8000/v1/audio/speech \
-H "Content-Type: application/json" \
-d '{
"model": "inclusionAI/Ming-3.0-tts-tiny",
"input": "Get the trust fund to the bank early.",
"response_format": "mp3",
"temperature": 0.8,
"max_new_tokens": 40,
"seed": 7
}' \
--output speech.mp3
Voice cloning#
ref_audio is one recording. A bare path is read by the server from its working directory, so start the server at the repository root when the path is tests/data/query_to_cars.wav. A data: URL is also accepted. A second reference is rejected.
Use curl
curl -X POST http://127.0.0.1:8000/v1/audio/speech \
-H "Content-Type: application/json" \
-d '{
"model": "inclusionAI/Ming-3.0-tts-tiny",
"input": "Get the trust fund to the bank early.",
"ref_audio": "tests/data/query_to_cars.wav",
"ref_text": "how many cars are there in the picture",
"response_format": "wav",
"seed": 123
}' \
--output cloned.wav
Use Python
import requests
response = requests.post(
"http://127.0.0.1:8000/v1/audio/speech",
json={
"model": "inclusionAI/Ming-3.0-tts-tiny",
"input": "Get the trust fund to the bank early.",
"ref_audio": "tests/data/query_to_cars.wav",
"ref_text": "how many cars are there in the picture",
"response_format": "wav",
"seed": 123,
},
timeout=180,
)
response.raise_for_status()
open("cloned.wav", "wb").write(response.content)