最初の項目は常にピンの出典です。全体の確度は、各資料が上記の開始・終了時刻をどれだけ強く裏付けているかの加重平均です。最新の資料より180日古くなるごとに、重みは半分になります。
ScriptByAI's[4] timeline dates Video 2.6 to 3 December 2025, two days after Video O1; the press release is datelined Beijing, 4 December ("today unveiled"), a time-zone difference.
5 December 2025: visuals, dialogue and sound effects in a single workflow.[1]
21 December 2025: voice control with custom voices, 3-30 second motion-control references, and API prices of about $0.07 to $0.14 per second on partner platforms.[1]
Dates VIDEO 2.6 to 3 December 2025 with Chinese and English voices and clips up to 10 seconds, and Voice Control to 16 December.[1]
足りない点や誤りがありますか？ このピンを裏付けるリンク、別の開始日・終了日とその理由、欠けている情報や誤っている情報を、自由に書いてください。AIがこのピンの出典と照らし合わせ、より良い情報源を探し、裏付けとなるページがあれば参考資料として追加します。ピン自身の出典が引き続き最も重視されます。AIは画像も確認します。別のものが写っている画像や写りの悪い画像は、後ろに回すか差し替えます。
| Spec |
|---|
| Value |
|---|
| 2.6 Pro, audio off | $0.07 per second (USD) |
|---|---|
| 2.6 Pro, audio on | $0.14 per second (USD) |
| 5 s with audio | $0.70 (USD) |
| 10 s with audio | $1.40 (USD) |
Prices as listed on the fal.ai endpoint page, read 24 Oct 2026. · 出典
| Spec | Kling 2.5 Turbo | Kling 2.6 |
|---|---|---|
| Native audio | No joint audio published | Yes, English and Chinese |
2.6 is described by Kling as its model with native audio; the 2.5 Turbo release does not mention audio. · 出典
Kling 2.6 is currently the state-of-the-art for public AI video generation.
Veed took exactly 1 minute and 25 seconds to create the five-second video.
Google Deepmind's Veo 3.1 follows at 0.480, Runway Gen-4 Turbo lands at 0.403, and Kuaishou's Kling 2.6 comes in at 0.369.
Like Google's Veo 3 or Sora 2, the model can generate sound effects that match video content, including voices and music.
