Voiceovers, music and sound effects

Audio lives at Audio. Voiceovers use Fish Audio S2 Pro by default, you can design a voice from a description or clone your own, and you can generate music and sound effects for your videos.

Voiceovers

• The default voice engine is Fish Audio S2 Pro.
• Older ElevenLabs voices remain available for existing work.
• Seed Audio is available for directed audio scenes.

Voiceovers are cheap. Fish voiceovers cost 375 credits per million bytes of script, with a minimum of 1 credit, so a short script costs 1 credit.

Custom voices

• Design a voice: describe the voice you want, such as age, accent and tone.
• Clone your own voice: record or upload a sample of your voice.

Only clone a voice you own or have permission to use. See the Content Policy.

Music

Generate background music from a description of mood, genre and tempo. Music costs 4 credits per 30 seconds.

Sound effects

Generate sound effects such as whooshes, clicks or ambience. Sound effects cost 1 credit per 5 second block.

Licensing

Plans include a commercial license, and that includes the rights to music you generate.

Tips

• Write scripts the way people speak.
• Add punctuation to control pauses.
• Keep music descriptions short: mood, genre, tempo.

Using audio with video

• Add a voiceover to a product video or a UGC ad.
• Lay music under a Flow or a Director mode commercial.
• Use sound effects to punctuate cuts and transitions.

Every audio model also works inside Flows, and the cost is always shown before you generate, so you can budget a full campaign up front.

Quick answers

What is the default voice engine?

Fish Audio S2 Pro.

How much does a voiceover cost?

375 credits per million bytes of script, minimum 1 credit. Most short scripts cost 1 credit.

How much does music cost?

4 credits per 30 seconds.

Can I use the music commercially?

Yes. The commercial license includes music rights.