Every audio model
One workspaceDifferent voices
Claire
Warm, close, unhurried
Oliver
Measured, for long-form narration
Eleanor
Clear and instructional
Graham
Bright, quick, forward-leaning
Anjali
Even and welcoming
Hana
Precise, good for information
Generate speech in three steps
- 01
Open Morphic
Sign up and start creating on a free-flowing, infinite visual canvas.
- 02
Cast a voice, paste the script
Pick from 95 voices across fourteen languages. Up to 2,000 characters a pass.
- 03
Generate and refine
Speech comes back in under a second. Swap voices, change tiers, or keep going on the Canvas.
What Inworld TTS 2 generates
Characters that answer in real time
Median time to first audio is under 200 milliseconds, so speech starts while the conversation is still live. That is the difference between a character that talks and one that waits.
One brand voice, every market
Run the same script through the same voice in language after language. The identity holds across the switch, so a campaign sounds like one narrator worldwide instead of a different hire per region.
A cast, not a voice
Ninety-five voices across fourteen native languages is enough to fill a village without reusing the same one twice. Cast each part once and the voices stay put across every revision.
Long-form, kept consistent
Work through a book or a course a passage at a time, up to 2,000 characters a pass. The cast voice holds steady from the first chapter to the last.
Time-freeze effect
Cinematic time-freeze short film for any scene
Messages to cinematic scene
Dramatize any text conversation into a cinematic multi-shot video.
Renovation timelapse
Photo of any real-estate becomes a cinematic renovation timelapse video with construction SFX and music.
Cinematic storyboard
Share a scene description with character references. Get a full storyboard with shot angles and mood.
Dance your character
Upload a character image and make it dance in any style.
Put yourself in a movie
Drop in a photo of yourself. Get a 12-second cinematic movie with animation and a matched soundtrack.
All on Morphic
Your complete audio stackInworld TTS 2
The full model page: the two tiers, the 95-voice catalog, the language reach, and the limits worth knowing first.
Voice and dialogue
Narration, character voices, and scripted conversation across every speech model in one prompt bar.
Effects and ambience
One-shot impacts and looping ambience beds, generated from the same prompt bar as your voice tracks.
Workflows
Turn any repeatable audio job into a one-click rerun. Save it as a Workflow, then share or rerun it anytime.
