Voices & Music

U-Gen provides 1,200+ voices across 29 languages for video narration, plus a curated background music library with custom upload support. Voice-over is generated using ElevenLabs Speech-to-Speech (STS).

Voice library

1,200+

Unique voices (600 female + 600 male)

Languages including Arabic, French, Japanese, Korean, Hindi

STS v2

ElevenLabs eleven_multilingual_sts_v2 model

Voice Override

Each persona has a default voice. You can pick a different voice in the Advanced step of the wizard — the job-level voice always takes priority over the persona default.

Background music

Add background music from the built-in library or upload your own tracks. Music is mixed with the voice-over at a reduced volume (15%) so narration stays clear.

Built-in library

Browse royalty-free tracks by mood: calm, upbeat, energetic, professional, cinematic, trendy, and more. Preview each track before selecting.

Custom uploads

Upload your own music files (MP3, WAV, OGG, AAC, or M4A — max 20 MB). Custom tracks are private to your account and reusable across jobs.

Audio Mixing

Background music plays at 15% volume by default and fades in/out automatically. The voice-over track always takes priority in the final mix.

Available moods

Filter the built-in library by mood:

calmupbeatenergeticprofessionalelegantwarminspiringplayfulsophisticateddramaticchillconfidenttrendyneutralcinematic

API access

Manage voices and music programmatically via the Voices API and Music API.