No filming:An AI avatar or clone yourself
    Versely

    Inworld · Audio model

    Inworld TTS 2 Flash: specs, pricing and how to use it

    Inworld Realtime TTS-2 Flash: the low-latency tier of TTS-2, around five times faster to first audio and 40% cheaper, with the same 200+ languages and voice cloning. Best for high-volume and conversational use.

    2 credits per 1,000 characters#13 overallFeatured
    Start free on the webDownload on theApp Store

    Free on the web and on iPhone, one account.

    What Inworld TTS 2 Flash is best at

    Text to audio
    Text to SpeechFastLow latencyMultilingual200+ languagesVoice CloneValue

    Pricing

    Inworld TTS 2 Flash 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

    Inworld TTS 2 Flash ranks #13 overall with an Elo score of 1218 on Versely's live model rankings.

    CategoryRankEloMeasured
    Text to audio#131218-

    Release

    Inworld TTS 2 Flash was released on September 2, 2026 (released 2 months ago).

    Other audio models

    Inworld TTS 2Inworld2 crInworld Voice CloneInworld2 crEleven v4ElevenLabs7 crCartesia Sonic 3.6Cartesia4 cr

    Use Inworld TTS 2 Flash inside these tools

    AI Text to SpeechAI Voice Cloning & Text to SpeechAI Music Generator

    Frequently asked questions

    How much does Inworld TTS 2 Flash cost on Versely?+

    Inworld TTS 2 Flash costs 2 credits per 1,000 characters on Versely.

    What is Inworld TTS 2 Flash best for?+

    Inworld Realtime TTS-2 Flash: the low-latency tier of TTS-2, around five times faster to first audio and 40% cheaper, with the same 200+ languages and voice cloning. Best for high-volume and conversational use. On Versely it is filed as a Inworld audio model for text to audio.

    When should I use Inworld TTS 2 Flash?+

    Use TTS-2 Flash for conversational and high-volume reads where speed-to-first-audio matters. Keep flagship TTS-2 for the most expressive character passes. Both sit under AI text to speech on Versely.

    How does Inworld TTS 2 Flash rank against other audio models?+

    Inworld TTS 2 Flash ranks #13 overall with an Elo score of 1218 on Versely's live model rankings.

    Does Inworld TTS 2 Flash need a voice sample?+

    No. Inworld TTS 2 Flash generates audio from a text prompt alone.

    Try Inworld TTS 2 Flash 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.

    Start free on the webDownload on theApp Store

    Free on the web and on iPhone, one account.

    Guides