InferX Beta Serverless GPU Inference Platform, Built for Agent-Native Workloads

Qwen3-TTS-12Hz-1.7B-Base

A lightweight text-to-speech model designed for efficient, high-quality speech synthesis
Qwen audio text2audio audio speech

Qwen3-TTS-12Hz-1.7B-Base is a 1.7B parameter text-to-speech model from the Qwen3 family, designed to generate natural-sounding speech with low latency and efficient resource usage, making it suitable for real-time voice assistants, agents, and scalable production deployments.

Log in to deploy: this public page shows the catalog model details, but deployment and customization stay behind login.
Log in to deploy

Metadata

Provider
Qwen
Modality
audio
API type
text2audio
Source
Created
2026-03-30 00:44:54 UTC
Updated
2026-04-18 14:40:31 UTC
Catalog version
3
Visibility
Published

Specifications

Parameters
MoE
No
Max model length
Image
vllm/vllm-omni:v0.16.0

Default Deploy Config

GPU count
1
vRAM
20000 MB
Summary
1xGPU 20000 MB

Recommended Use Cases

  • Text-to-speech

Model Spec