Models/Collections/Build voice & avatar systems

Build voice & avatar systems

Speech synthesis, avatar video, and lip sync models for character systems.

Text-to-speech

View all

Conversational text-to-speech with realtime voice direction and audio-aware delivery

$0.000035/ character
Run

Promptable full-song generation with vocals, lyrics, BPM and key control

$0.15/ request
Run

High-quality text-to-speech with expressive, natural voice synthesis

$0.0001/ characterHD
Run

AI avatars

View all

Lip-synced talking video from one portrait and an audio track or script, up to 3 minutes and 4K

$0.02/ second480p
Run

Cognitive avatar video from image, audio, and text

$0.13247/ second
Run

High fidelity avatar video generation with smoother motion and quality

$0.087/ second
Run

Lip sync

View all

Full-scene lip synchronization with global face understanding and obstruction handling

$0.133/ second
Run

High-resolution diffusion-based lip-sync editing up to 4K

$0.0733/ second
Run

Zero-shot audio-driven lip synchronization for video

$0.044/ second
Run

Model guides

Inworld Realtime TTS-2

Formatting LLM output for speech

How to write LLM system prompts that produce text TTS-2 can synthesize naturally, with normalization, filler words, and emphasis cues handled before the audio call.

Read the guide →
Inworld Realtime TTS-2

Controlling voice delivery with steering tags

How to use natural-language steering tags to control emotion, pacing, volume, and vocal style in TTS-2 speech output.

Read the guide →