Make songs, voices, and sound.
Music, voices, and sound effects from 16 models of 9 makers, in the same app as your chats.
Music, voice, and sound.
The three tabs of the Audio page of the app.
Music
Write a song with Lyria 3 Pro, or a short clip with Lyria 3 Clip.
- ElevenLabs
- Microsoft
- Fish Audio
- Mistral AI
- MiniMax
Voice
Give a script a voice with Eleven v4, Gemini 3.8 Flash TTS, MAI-Voice 2.1, Voxtral TTS 3, and more.
Sound
Make a sound effect from a few words with Seed Audio 1.0.
Pay per song or second.
Each price is about what one unit costs: a song, 1,000 characters read aloud, or one second of audio.
| Model | Mode | Price |
|---|---|---|
| Lyria 3 Pro | Music · Open | $0.10 a song |
| Lyria 3 Clip | Music · Open | $0.05 a song |
| Eleven v4 | Voice · ZDR | $0.10 per 1,000 characters |
| Gemini 3.8 Flash TTS | Voice · ZDR | $0.000281 a second |
| MAI-Voice 2.1 | Voice · ZDR | $0.027 per 1,000 characters |
| S2.1 Pro | Voice · ZDR | $0.019 per 1,000 characters |
| Voxtral TTS 3 | Voice · ZDR | $0.016 per 1,000 characters |
| Speech 2.8 HD | Voice · Open | $0.125 per 1,000 characters |
| Grok Voice TTS 1.0 | Voice · Open | $0.019 per 1,000 characters |
| Seed Audio 1.0 | Sound · ZDR | $0.003125 a second |
How private it is
Most voices run with zero data retention: the provider reads your script to speak it and keeps nothing. The music of Lyria 3 and the voices of MiniMax and Grok run in Open, where the provider may keep a request for a while. Your audio stays in your browser, out of any backup.