Instructions to use Serialtechlab/dhivehi-orpheus-tts-v8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Serialtechlab/dhivehi-orpheus-tts-v8 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Serialtechlab/dhivehi-orpheus-tts-v8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Serialtechlab/dhivehi-orpheus-tts-v8")
model = AutoModelForCausalLM.from_pretrained("Serialtechlab/dhivehi-orpheus-tts-v8", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Serialtechlab/dhivehi-orpheus-tts-v8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Serialtechlab/dhivehi-orpheus-tts-v8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Serialtechlab/dhivehi-orpheus-tts-v8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Serialtechlab/dhivehi-orpheus-tts-v8

SGLang

How to use Serialtechlab/dhivehi-orpheus-tts-v8 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Serialtechlab/dhivehi-orpheus-tts-v8" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Serialtechlab/dhivehi-orpheus-tts-v8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Serialtechlab/dhivehi-orpheus-tts-v8" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Serialtechlab/dhivehi-orpheus-tts-v8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Serialtechlab/dhivehi-orpheus-tts-v8 with Docker Model Runner:
```
docker model run hf.co/Serialtechlab/dhivehi-orpheus-tts-v8
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Dhivehi TTS (Orpheus-3B)

Prompt format is f"{speaker}: {text}". The speaker is a LEARNED NAME, not a reference clip, so voice identity does not decay over a long generation.

Production voices

female_01
female_02
female_03
female_05
female_06
female_07
male_01
male_03
male_04
male_05
cv_b6a0f9e42cb9

Any other name will still generate audio - the model improvises - so callers must validate against this list rather than trusting that a bad name fails loudly.

Downloads last month: 6

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for Serialtechlab/dhivehi-orpheus-tts-v8

Base model

meta-llama/Llama-3.2-3B-Instruct

Finetuned

canopylabs/orpheus-3b-0.1-pretrained

Finetuned

canopylabs/orpheus-3b-0.1-ft

Finetuned

unsloth/orpheus-3b-0.1-ft

Finetuned

(299)

this model