読書リサーチレーダー投資フレームワーク
ログイン / 新規登録
← 読解に戻る
ニューストピック · Suno语音功能クイックテイク1 分で読めるDisconfirmAI 編集部

Suno's new feature generates speech with matching music, training method still undisclosed

Speech-with-score single-track generation widens AI audio creation, but the undisclosed training method matters amid ongoing copyright litigation.

2026-10-02 04:35 GMT+8

Suno released the Speech beta on October 1, generating spoken audio and matching background music together in a single track.

Users type an idea or text and describe the voice and music style; the model produces both the voice and the score. The company says it suits poems, meditations and bedtime stories, and admits the beta still has bugs — a British accent can occasionally wander off to Australia.

Suno has not said how it trained the model. The company is being sued by major record labels, and a Munich court recently rejected its fair use defense.

ソース

  • suno.com↗
トピック

Suno语音功能

美国AI音乐平台Suno于2026年10月推出“Speech”公测版,首次实现人声旁白与背景音乐的同步生成。该功能允许用户通过文本提示或脚本创建带有配乐的口语音频,旨在将创作范围从歌曲扩展至更广泛的音频表达。【背景】与此同时,瑞典流媒体巨头…

3 ステップ3 件更新日 2026-11-13 18:57

経緯

  1. 2026-10-01Suno首席产品官Jack Brody宣布推出Speech(beta),定位为能同时生成人声和音乐的音频模型。
ログイン / 新規登録
読書リサーチレーダー投資フレームワーク
suno.com ↗
  • 2026-10-02The Verge报道Suno Speech功能上线,指出其支持简单模式(描述)和高级模式(自定义脚本),最长时长约8分钟。theverge.com ↗
  • 2026-11-10TechCrunch报道Spotify为AI DJ增加7种英语和2种西班牙语语音人格,以及“少废话”模式,面向Premium用户推送。techcrunch.com ↗
  • 未解決の問題

    • Suno Speech模型的训练数据来源是否涉及未经授权的版权内容?
    • Suno是否会公开Speech功能的详细技术参数或基准测试结果?
    • Spotify AI DJ的新语音人格是否会影响其现有推荐算法的用户留存率?

    このスレッド内の他の記事

    • Spotify AI DJ Adds Customizable Voices and 'Less Chatter' Mode for Premium Users2026-11-10
    • Suno opens its Speech feature in beta, generating voice and music in one track2026-10-02
    トピック全文を読む →
    リサーチを続ける →