# Sound and music

Period: 2023 – now · Era: 2023 · The Cambrian Explosion

Voice, sound effects and score, then sound in the same pass as the picture.

For two years AI films were silent until someone scored them. Creators cut to stock music, then generated whole songs with Suno and Udio (spring 2024) and sound effects with ElevenLabs (May 2024), layering them under silent clips. In May 2025 Veo 3 made dialogue, effects and ambience in the same pass as the picture, and by 2026 models took music and sound as references. Many music videos and trailers still start with the song.

## How it worked

1. **Pick or make the music first** when the film is cut to it, and map its beats before generating anything.
2. **Let the model make the sound** when it can: native dialogue, effects and ambience (Veo 3, Kling 3.0, Seedance), with separate stems where offered.
3. **Layer what it misses:** effects prompted per shot in ElevenLabs, voices from a fixed cloned voice per character.
4. **Score with a music model** (Suno, Udio, ElevenLabs Music) and keep the stems so the mix stays editable.
5. **Mix under the voice** in the editor; sound often covers more cuts than a picture fix.

## Why it mattered

Sound is half the film. Generated music and effects let one person finish a piece, and native audio removed the step that made AI scenes feel dubbed.

## Tools of the era

- Suno v3 (2024): https://suno.com
- Udio (2024): https://www.udio.com
- ElevenLabs Sound Effects (2024): https://elevenlabs.io/sound-effects
- Veo 3 (2025): https://deepmind.google/models/veo/
- Eleven v3 (2025): https://elevenlabs.io
- Seedance 2.0 (2026): https://seed.bytedance.com/en/seedance
- ElevenLabs MCP (2026): https://elevenlabs.io/blog/introducing-voice-music-image-and-video-generation-in-the-elevenlabs-mcp

## Example videos and posts

- Veo 3 and Flow: native audio inside a director app · Theoretically Media: https://www.youtube.com/watch?v=oSerkVI-s84
- Genesis: 316 prompts, 310 clips, 44 used · Nicolas Neubert: https://x.com/iamneubert/status/1684989102213476359
- ElevenLabs MCP and Claude: the ultimate creative unlock · DesignCourse: https://www.youtube.com/watch?v=SdumUqJ3EN0
- Three ways to keep a voice consistent across generations · Curious Refuge: https://www.youtube.com/watch?v=3qDL7A4sS2k

## On the timeline

- [BMG and Suno Announce a Global Strategic Alliance](https://aifilmhistory.org/entry/bmg-suno-alliance) (2026-08-12)
- [Seed Audio 1.0](https://aifilmhistory.org/entry/seed-audio-1-0) (2026-06-30)
- [ElevenLabs Instant Soundtracks](https://aifilmhistory.org/entry/elevenlabs-instant-soundtracks) (2026-10-15)

## Sources

- ElevenLabs launches text-to-sound-effects: https://voicebot.ai/2024/06/03/elevenlabs-launches-generative-ai-text-to-sound-effects-tool/

---
Source: https://aifilmhistory.org/workflows/craft-sound