Qwen · Audio model

    Qwen 3 TTS 1.7B

    High-quality text-to-speech model with enhanced naturalness and emotional expression

    2 credits per 1,000 characters#85 overall

    What Qwen 3 TTS 1.7B is best at

    Text to audio
    Text to speechMultilingualEmotional voice

    Pricing

    Qwen 3 TTS 1.7B costs 2 credits per 1,000 characters on Versely. It bills per 1,000 characters of input text.

    OptionPrice
    per 1,000 characters2 credits

    Prices are Versely credits. Your plan's credit allowance is on the pricing page.

    Inputs

    Text prompt

    Generates from a written prompt — no media upload required.

    Rankings

    Qwen 3 TTS 1.7B ranks #85 overall with an Elo score of 926 on Versely's live model rankings.

    CategoryRankEloMeasured
    Text to audio#85926

    Release

    Qwen 3 TTS 1.7B was released on January 21, 2026released 8 months ago.

    Other audio models

    Use Qwen 3 TTS 1.7B inside these tools

    Frequently asked questions

    How much does Qwen 3 TTS 1.7B cost on Versely?+

    Qwen 3 TTS 1.7B costs 2 credits per 1,000 characters on Versely.

    What is Qwen 3 TTS 1.7B best for?+

    Qwen 3 TTS 1.7B is a Qwen audio model built for text to audio.

    How does Qwen 3 TTS 1.7B rank against other audio models?+

    Qwen 3 TTS 1.7B ranks #85 overall with an Elo score of 926 on Versely's live model rankings.

    Does Qwen 3 TTS 1.7B need a voice sample?+

    No. Qwen 3 TTS 1.7B generates audio from a text prompt alone.

    When was Qwen 3 TTS 1.7B released?+

    Qwen 3 TTS 1.7B was released on January 21, 2026 (released 8 months ago).

    Try Qwen 3 TTS 1.7B inside Versely

    The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync — in your browser or on your phone.