Skip to content

    Qwen3-TTS 12Hz 1.7B CustomVoice

    Text-to-Speech

    Qwen3-TTS-12Hz-1.7B-CustomVoice

    Qwen3-TTS 12Hz 1.7B CustomVoice on FlexAI: Alibaba TTS, Apache 2.0 license, deployable as a dedicated FlexAI or self-hosted endpoint.

    Pricing and availability

    Qwen3-TTS 12Hz 1.7B CustomVoice rates on FlexAI, in US dollars. Quoted per GPU-hour on dedicated GPUs rather than per token, billed per minute, and autoscaling with your traffic.
    RatePrice
    Configuration1× H100
    Endpoint rate$4.33 / hour(for 1 GPU at $4.33 per hour)
    AvailabilityDedicated endpoint, provisioned per customer

    Deployment requirements

    API endpoint
    /v1/audio/speech
    Compatibility
    OpenAI
    Parameters
    1.9B
    Active parameters
    1.7B of 1.916676B
    License
    Apache 2.0
    Hardware
    H100
    GPUs to self-host
    1× H100
    Native precision
    BF16, from safetensors
    Weights
    Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
    Published by
    Alibaba
    Origin
    China

    Qwen3-TTS 12Hz 1.7B CustomVoice runs as a dedicated endpoint, provisioned per customer on FlexAI's infrastructure or your own, not served through the shared Token Factory API.