conv.

All stories
AIQuiet 2d · day 3

Google launches benchmark-topping text-to-speech models

Gemini 3.8 Flash and Flash-Lite TTS now available on Google Cloud, supporting 130 and 101 languages respectively.

newest coverage 2d agosummary written 2d ago2 pieces NewswiresGoogle News

What to know

  • Google released Gemini 3.8 Flash TTS and Flash-Lite TTS, dual text-to-speech models optimized for quality and cost efficiency respectively, now available on Google Cloud.
  • Both models ranked first and second on independent audio quality benchmarks and support customization through 2,000+ prepackaged voices or synthetic voice generation from audio samples.
  • Google embedded SynthID watermarking and C2PA metadata in all generated speech to enable detection of AI-generated content and document its creation history.

“Flash-Lite TTS is optimized for cost-cost efficiency and inference speed. Flash TTS offers better audio quality for a higher price.”

SiliconANGLE, Reporter · SiliconANGLE

Google LLC AI model developerLeland Rechis Google stafferAlan Cowen Google staffer

Google launches benchmark-topping text-to-speech models
siliconangle.com

How it unfolded 1 development · click the chart to see its coverage articles

Peak 1 piece in one hour at Sep 23, 11 AM; 2 pieces over 3 days (2 articles) Sep 23, 11 AM — 1 piece · 1 article — Newswires 1Sep 23, 12 PM — quietSep 23, 1 PM — quietSep 23, 2 PM — quietSep 23, 3 PM — quietSep 23, 4 PM — quietSep 23, 5 PM — quietSep 23, 6 PM — quietSep 23, 7 PM — quietSep 23, 8 PM — 1 piece · 1 article — Google News 1Sep 23, 9 PM — quietSep 23, 10 PM — quietSep 23, 11 PM — quietSep 24, 12 AM — quietSep 24, 1 AM — quietSep 24, 2 AM — quietSep 24, 3 AM — quietSep 24, 4 AM — quietSep 24, 5 AM — quietSep 24, 6 AM — quietSep 24, 7 AM — quietSep 24, 8 AM — quietSep 24, 9 AM — quietSep 24, 10 AM — quietSep 24, 11 AM — quietSep 24, 12 PM — quietSep 24, 1 PM — quietSep 24, 2 PM — quietSep 24, 3 PM — quietSep 24, 4 PM — quietSep 24, 5 PM — quietSep 24, 6 PM — quietSep 24, 7 PM — quietSep 24, 8 PM — quietSep 24, 9 PM — quietSep 24, 10 PM — quietSep 24, 11 PM — quietYesterday, 12 AM — quietYesterday, 1 AM — quietYesterday, 2 AM — quietYesterday, 3 AM — quietYesterday, 4 AM — quietYesterday, 5 AM — quietYesterday, 6 AM — quietYesterday, 7 AM — quietYesterday, 8 AM — quietYesterday, 9 AM — quietYesterday, 10 AM — quietYesterday, 11 AM — quietYesterday, 12 PM — quietYesterday, 1 PM — quietYesterday, 2 PM — quietYesterday, 3 PM — quietYesterday, 4 PM — quietYesterday, 5 PM — quietYesterday, 6 PM — quietYesterday, 7 PM — quietYesterday, 8 PM — quietYesterday, 9 PM — quietYesterday, 10 PM — quietYesterday, 11 PM — quietToday, 12 AM — quietToday, 1 AM — quietToday, 2 AM — quietToday, 3 AM — quietToday, 4 AM — quietToday, 5 AM — quietToday, 6 AM — quiet 1
Sep 24yesterdaynow · 7:07 AM ET
  1. 1

    Google releases Gemini 3.8 Flash and Flash-Lite TTS models

    Google made two new text-to-speech models available through its cloud platform. Flash TTS supports 130 languages and prioritizes audio quality, while Flash-Lite TTS supports 101 languages and is optimized for cost efficiency and speed. Both offer access to over 2,000 prepackaged voices and allow developers to create custom voices using natural language prompts or 30-second audio samples.

    “These models enable creators, developers, and enterprises to create richer, more expressive audio experiences, while enabling improved user experiences in products like Gemini Notebook and Google Vids.”
    — Leland Rechis and Alan Cowen
    1. 1 outlet Google launches two benchmark-topping speech generation models

      first by SiliconANGLE, 2d ago

  2. background

    Google embeds watermarking and metadata in generated speech — The models use SynthID technology to embed inaudible audio watermarks detectable by AI tools, and attach C2PA records to all generated audio files to document creation time, modification status, and related metadata.

  3. background

    Models rank first and second on audio quality benchmarks — Flash TTS and Flash-Lite TTS earned the top two positions on an audio quality benchmark developed by Hume AI Inc., and outperformed competing models on multiple versions of the Voice Arena benchmark that measures speech quality based on human feedback.