AI audio models
Text-to-speech, music generation and speech-to-text.
GE
Gemini TTS
Audioby Google
3 models · from 80 credits
GR
Grok Speech
Audioby xAI
2 models · from 4 credits
MI
MiniMax Speech
Audioby MiniMax
2 models · from 96 credits
EL
ElevenLabs
Audioby ElevenLabs
1 model · from 200 credits
MI
MiniMax Music
Audioby MiniMax
1 model · from 300 credits
SE
Seed Audio
Audioby ByteDance
1 model · from 572 credits
Audio · 10
| Model | Mode | Price | Aspect ratios | |
|---|---|---|---|---|
| ElevenLabs v3 Text-to-Speech | Text to speech | from 200 credits | — | Open → |
| xAI TTS v1 | Text to speech | from 30 credits | — | Open → |
| MiniMax Speech 2.6 HD | Audio | from 160 credits | — | Open → |
| MiniMax Speech 2.6 Turbo | Audio | from 96 credits | — | Open → |
| Gemini 3.1 Flash TTS | Text to speech | from 300 credits | — | Open → |
| Seed Audio 1.0 | Audio | from 572 credits | — | Open → |
| MiniMax Music 2.6 | Music | from 300 credits | — | Open → |
| xAI STT v1 | Speech to text | from 4 credits | — | Open → |
| Gemini 2.5 Flash TTS | Text to speech | from 80 credits | — | Open → |
| Gemini 2.5 Pro TTS | Text to speech | from 160 credits | — | Open → |