Audio Lab model directory

AI audio models for voice, music, and sound effects.

Audio Lab puts narration, music, and sound effect models in one workspace. Pick the job, pick the model, see the quote, and download the audio. There is no single best model: start from the job, then the voice, length, or vocals you need.

Editorial selection · Last reviewed 30 October 2026

Voice

A script read by a voice you choose.

ElevenLabs

Eleven v4 Turbo

Fast, natural v4 narration.

Voices12 named Clip Studio voices
ScriptUp to 5,000 characters
See model
ElevenLabs

Eleven v4

The most expressive ElevenLabs read.

Voices12 named Clip Studio voices
ScriptUp to 5,000 characters
See model
ElevenLabs

Eleven Flash v2.5

Fast, plain text-to-speech narration.

Voices12 named Clip Studio voices
ScriptUp to 5,000 characters
See model
Google

Gemini 3.8 Flash TTS

Google text-to-speech with 30 prebuilt voices.

Voices30 prebuilt Gemini voices
ScriptUp to 5,000 characters
See model
Google

Gemini 3.8 Flash Lite TTS

The lighter Gemini voice model.

Voices30 prebuilt Gemini voices
ScriptUp to 5,000 characters
See model
HeyGen

HeyGen Voice

HeyGen text-to-speech in 24 voices and 39 languages.

Voices24 HeyGen voices, 39 languages
ScriptUp to 5,000 characters
See model
HeyGen

HeyGen Voice Turbo

The fast, lighter HeyGen read.

Voices24 HeyGen voices, 39 languages
ScriptUp to 5,000 characters
See model

Music

A track from a description, with or without lyrics.

Google DeepMind

Lyria 3.5

Full songs or instrumentals from a description.

LengthSet in your prompt
VocalsYour lyrics, as described, or instrumental
See model
MiniMax

MiniMax Music 3

Songs with your own lyrics, up to five minutes.

Length30s · 1 min · 2 min · 3 min · 5 min
VocalsFrom your lyrics, or instrumental
See model
Mureka

Mureka 9

Full songs from your lyrics, or instrumentals.

LengthSet by the model
VocalsFrom your lyrics, or instrumental
See model

Sound effects

Foley and ambience from a description.

Mirelo

Mirelo SFX 2.0

Foley, ambience, and hits from a description.

Length3s · 5s · 10s · 20s · 30s
PromptUp to 2,000 characters
See model
Questions, answered

AI audio models FAQ

11 models. Voice: Eleven v4 Turbo, Eleven v4, Eleven Flash v2.5, Gemini 3.8 Flash TTS, Gemini 3.8 Flash Lite TTS, HeyGen Voice, HeyGen Voice Turbo. Music: Lyria 3.5, MiniMax Music 3, Mureka 9. Sound effects: Mirelo SFX 2.0.

Eleven v4 Turbo for a fast, natural read with audio tags in the 12 named Clip Studio voices. Eleven v4 for the most expressive delivery, Eleven Flash v2.5 for the plainer read of the earlier fast model, the Gemini models for Google's 30 prebuilt voices, and the HeyGen models for 24 HeyGen voices in 39 languages.

Lyria 3.5 for songs or instrumentals described in a prompt. MiniMax Music 3 for a song sung from your own lyrics at an exact length, up to five minutes. Mureka 9 for a full song from your lyrics when the model can pick the length.

No. Every plan includes Audio Lab and every model in it. Each run is quoted before you generate and uses your monthly generation allowance. Clip Pro from $19/mo.

No. You use every model from your Clip Studio account, and the audio lands in your Clip Studio library.