AI audio models
Voiceover and music models for your videos, available through the Advibly MCP server. Compare voices, lengths and credits.
Explore the library
6 of 6 models
- xAIAudio
xAI TTS
xAI's expressive text-to-speech for multilingual voiceovers, with five voices and 20 language variants.
Voiceovers in many languages - CartesiaAudio
Cartesia Sonic 3.6
Cartesia's natural, low-latency text-to-speech with a large library of voices.
Natural narrator voices - ElevenLabsAudio
ElevenLabs Eleven v4
ElevenLabs' expressive text-to-speech, with audio tags that direct how each line is read.
Expressive, directed voiceovers - ElevenLabsAudio
ElevenLabs Eleven v4 Turbo
The Turbo variant of ElevenLabs Eleven v4: the same voices and audio tags at half the price per character.
ElevenLabs voices at volume - MiniMaxAudio
MiniMax Music 3
MiniMax's music model for complete tracks of up to five minutes from a style prompt, with optional written lyrics.
Songs with your own lyrics - ElevenLabsAudio
ElevenLabs Music v2.5
ElevenLabs' music model for polished, prompt-described tracks of up to ten minutes.
Polished score from a description
Prices are estimates from Advibly's live model configuration at $1 per credit. The composer shows the exact amount for your settings before anything is charged.