Adobe MAX 2025: New AI Audio Tools
Adobe is introducing new AI audio tools in Firefly specifically for video creators. Generate Soundtrack (in public beta) produces music tracks that sync with your video, allowing you to select a genre like hip-hop, EDM, or rhythm through simple descriptions. Meanwhile, Generate Speech helps create realistic voiceovers with over 50 voices and support for 20+ languages, with options to adjust speed, pitch, and emotion, making it easy to create natural-sounding narrative videos.
Generate Soundtrack
Generate Soundtrack (in public beta) automatically analyzes video and creates original instrumental soundtracks, synchronized with the edit, allowing for selection of vibe, genre, and intensity through simple descriptive prompts – from cinematic scores to EDM and hip-hop, with up to 5-minute tracks per prompt.
At the same time, all music tracks are fully licensed and “commercially safe”, since the Firefly Audio Model has been trained on licensed material, ensuring use in professional productions without risk of copyright claims.
Generate Speech
Also entering public beta is Generate Speech, a powerful text-to-speech tool within Firefly, which creates natural voiceovers in over 20 languages, with more than 50 voices via the Firefly Speech Model and ElevenLabs.
Creators can adjust speed, pitch, emotion and emphasis on specific words, correct pronunciation of names and produce clear narration directly from text, speeding up workflows for social videos, tutorials, commercials and explainers without the need for external voiceovers.
Learn more at www.adobe.com.
Comart is an Adobe Gold Reseller in the Commercial, Education & Government categories
