Models
Overview
All supported AI models for video, image, and audio generation
Supported Models
Synthome provides a unified interface to multiple AI models across providers. Use the same code pattern regardless of which model or provider you choose.
Video Models
| Model | ID | Providers | Use Case |
|---|---|---|---|
| Seedance 1 Pro | bytedance/seedance-1-pro | Replicate | Text-to-video, Image-to-video |
| Minimax Video 01 | minimax/video-01 | Replicate | Text-to-video |
| Fabric 1.0 | veed/fabric-1.0 | Fal | Lip-sync (talking head) |
import { videoModel, generateVideo } from "@synthome/sdk";
generateVideo({
model: videoModel("bytedance/seedance-1-pro", "replicate"),
prompt: "A sunset over the ocean",
});Image Models
| Model | ID | Providers | Use Case |
|---|---|---|---|
| Nano Banana | google/nano-banana | Replicate, Fal | Text-to-image, Image-to-image |
| Nano Banana Pro | google/nano-banana-pro | Replicate, Fal | Advanced generation, Typography |
| Seedream 4 | bytedance/seedream-4 | Replicate | High-resolution images |
| Background Remover | codeplugtech/background_remover | Replicate | Remove backgrounds |
import { imageModel, generateImage } from "@synthome/sdk";
generateImage({
model: imageModel("google/nano-banana", "replicate"),
prompt: "A mountain landscape at dawn",
});Audio Models
| Model | ID | Providers | Use Case |
|---|---|---|---|
| ElevenLabs Turbo | elevenlabs/turbo-v2.5 | ElevenLabs, Replicate | Text-to-speech |
| Hume TTS | hume/tts | Hume | Emotional text-to-speech |
| Whisper | openai/whisper | Replicate | Speech-to-text |
| Fast Whisper | vaibhavs10/incredibly-fast-whisper | Replicate | Fast transcription |
import { audioModel, generateAudio } from "@synthome/sdk";
generateAudio({
model: audioModel("elevenlabs/turbo-v2.5", "elevenlabs"),
text: "Hello, welcome to our video.",
voiceId: "21m00Tcm4TlvDq8ikWAM",
});Model Selection Pattern
All models follow the same pattern:
// Video
videoModel("model-id", "provider");
// Image
imageModel("model-id", "provider");
// Audio
audioModel("model-id", "provider");Provider Fallback
Some models are available on multiple providers. Choose based on:
- Cost: Pricing varies between providers
- Speed: Some providers are faster for certain models
- API Keys: Use providers where you already have accounts
// Same model, different providers
imageModel("google/nano-banana", "replicate");
imageModel("google/nano-banana", "fal");How is this guide?