Vocence TTS (Gem1832)
A prompt-driven text-to-speech model fine-tuned by Gem1832 on Qwen3-TTS-12Hz-1.7B-VoiceDesign.
Features
- Natural English speech synthesis
- Prompt-controlled voice characteristics
- 24 kHz mono WAV output
- Optimised for Bittensor SN78 (Vocence)
Usage
from qwen_tts import Qwen3TTSModel
import soundfile as sf
model = Qwen3TTSModel.from_pretrained("Gem1832/vocence-tts")
wavs, sr = model.generate_voice_design(
text="Hello, this is a test of the text-to-speech system.",
instruct="A clear, natural voice with conversational tone.",
language="english",
)
sf.write("output.wav", wavs[0], sr)
Prompt Examples
A man speaks calmly and naturally.
A woman with a warm, friendly tone.
A clear, neutral voice reading the sentence.
Fine-tuned by Gem1832
- Downloads last month
- 21