Wan: sound, voice or lip-sync, note by note

4 Wan entries on sound, voice or lip-sync, 23 September 2025 to 3 April 2026, across Wan 2.5, Wan 2.6 and Wan 2.7. The latest: Wan 2.7 reference-to-video mixes up to five image or video references and clones a voice timbre. As of 2026-09-25.

Inclusion rule. Lines with at least one entry of this kind. Order. Alphabetical by line.

The register holds 4 Wan entries on sound, voice or lip-sync; the first is dated 23 September 2025.

1The entries

23 September 2025, Wan 2.5

newly upgraded model architecture supports synchronized audio generation with visuals, enables 10-second long video generation

Alibaba Cloud Model Studio, newly released models

• wan2.5-t2v-preview
  Wan 2.5 preview generates synchronised audio and 10 second clipsAlibaba Cloud Model Studio, newly released models / since 2025-09-23 / checked 2026-09-25

3 December 2025, Wan 2.6

supports stable multi‑speaker dialogue with more natural and realistic vocal timbres

Alibaba Cloud Model Studio, newly released models

• wan2.6-i2v-us
  Wan 2.6 image-to-video handles dialogue between several speakersAlibaba Cloud Model Studio, newly released models / since 2025-12-03 / checked 2026-09-25

The gap from the previous entry: 71 days.

16 December 2025, Wan 2.6

supports using a specified person or any object as a reference, precisely maintaining consistency of appearance and voice, and allows multi‑character reference for joint performances.

Alibaba Cloud Model Studio, newly released models

• wan2.6-r2v
  Wan 2.6 reference-to-video keeps a person's look and voice, with several characters at onceAlibaba Cloud Model Studio, newly released models / since 2025-12-16 / checked 2026-09-25

It came 13 days after the previous one.

3 April 2026, Wan 2.7

Supports hybrid referencing of up to 5 mixed image/video inputs and audio timbre cloning.

Alibaba Cloud Model Studio, newly released models

• wan2.7-r2v
  Wan 2.7 reference-to-video mixes up to five image or video references and clones a voice timbreAlibaba Cloud Model Studio, newly released models / since 2026-04-03 / checked 2026-09-25

108 days after the entry before it.

2The same kind of change in other lines

• Google Veo: 1 entry, July 2025
• Grok Imagine: 2 entries, July 2026 to August 2026
• Kling AI: 7 entries, December 2024 to March 2026
• LTX: 3 entries, December 2025 to August 2026
• PixVerse: 4 entries, July 2025 to July 2026
• Vidu: 2 entries, July 2025 to November 2025

Wan, every entry · Sound, voice and lip-sync, every line · Wan 2.6 · Wan 2.7

3Notes read

• Alibaba Cloud Model Studio, newly released models, read 2026-09-25