Voice Models
Voice Models
Browse 14 speech, narration, and audio-ready models connected to the voice workspace.
Bound models
14
Providers
6
Access modes
2
Profile labels
1
Provider roster
Use Cases
Where this family is designed to work.
Narration, dubbing, speech transfer, and multilingual delivery.
Voice identity systems for creators, brands, and character-driven work.
Audio cleanup and spoken-content production tied to the same queue and usage surface.
Coverage
Every route in this family, with scan tools built in.
Search the family, tighten it by provider, access, or profile, then sort it by signal or name before opening a route.
3 featured bindings
5 credit floor
4 linked tools
Family routes
14
Providers
6
Profiles
1
Provider
Access
Profile
Sort rows
Provider distribution
Access distribution
Profile distribution
Signal score 33
Fish Audio TTS
OpenArt Collection · Balanced · Audio routed
Natural vocal expression profile with rich tone.
Open routeSignal score 33
Fish Audio V1.5
OpenArt Collection · Balanced · Audio routed
Balanced profile for clean and expressive spoken audio.
Open routeSignal score 33
GPT 4o Audio Preview
OpenArt Collection · Balanced · Audio routed
Experimental profile for multimodal voice quality tests.
Open routeSignal score 33
GPT 4o Mini TTS
OpenArt Collection · Balanced · Audio routed
Conversational profile optimized for short-form narration.
Open routeSignal score 33
Mini TTS
OpenArt Collection · Balanced · Audio routed
Lower-latency profile for quick previews and drafts.
Open routeSignal score 33
Playground TTS
OpenArt Collection · Balanced · Audio routed
Creative voice experimentation profile.
Open routeNatural vocal expression profile with rich tone.
Balanced profile for clean and expressive spoken audio.
Experimental profile for multimodal voice quality tests.
Conversational profile optimized for short-form narration.
Lower-latency profile for quick previews and drafts.
Creative voice experimentation profile.
General-purpose text-to-speech profile.
FAI.ai narration profile focused on polished long-form delivery and premium pacing.
Hyper-realistic voice cloning and expressive speech generation.
Full-song generation with rich vocal and instrumental composition.
High definition narration profile from OpenAI.
High-fidelity AI music generation with fine-grained segment control.
FAI.ai premium dubbing profile for rapid line-by-line scene performance.
FAI.ai starter voice profile for fast guided narration and drafts.
Related Tools
Where this family is used in ELYSIO.
Surface
AI Voice
Hub surface for speech, dubbing, cloning, and spoken-audio production.
/ai/voice
Surface
Text to Speech
Narration and spoken delivery across routed voice models.
/ai/voice/text-to-speech
Surface
Dubbing
Multi-line, multi-language dubbing workflows inside the audio lane.
/ai/voice/dubbing
Surface
Audio Studio
TTS, dubbing, music, and audio workflows in one place.
/studio/audio