AI Navigate
インサイト最新記事一覧AI大全

Mistral's first open-weight TTS model Voxtral clones voices from three seconds of audio across nine languages

THE DECODER / 3/27/2026

📰 NewsSignals & Early TrendsIndustry & Market MovesModels & Research
Read original →
共有:

Key Points

  • Mistral has released Voxtral, its first open-weight text-to-speech (TTS) model supporting nine languages.
  • Voxtral can clone a speaker’s voice using only three seconds of reference audio.
  • The release positions Mistral as a direct competitor in the fast-growing voice generation and TTS tooling space.
  • Because the model is open-weight, developers and researchers may be able to experiment with and adapt voice cloning workflows more easily.
  • The nine-language capability broadens potential real-world deployment scenarios beyond a single market or language.

French AI startup Mistral has released Voxtral TTS, its first text-to-speech model that supports nine languages and can clone voices from just three seconds of audio.

The article Mistral's first open-weight TTS model Voxtral clones voices from three seconds of audio across nine languages appeared first on The Decoder.

関連おすすめサービス

※当サイトはアフィリエイト広告を利用しています
🎧

Notta搭載AI議事録イヤホン ZENCHORD1

AI時代の仕事術。Notta搭載で会議の議事録を自動生成するスマートイヤホン。

🎙️

AI搭載ボイスレコーダー Plaud

世界100万人が愛用。AIで文字起こし・要約を自動化するボイスレコーダー。

🖼️

画像高画質化AIツール Aiarty Image Enhancer

AIで画像を高画質化。写真・イラストを簡単にアップスケール。

Mistral's first open-weight TTS model Voxtral clones voices from three seconds of audio across nine languages | AI Navigate