Models/Collections/Build realtime generation products

Build realtime generation products

Fast image generation, realtime speech, and prompt enhancement for interactive products.

Realtime image generation

View all

Fast, high-quality image generation and editing for everyday creative production

$5.00/ 1M tokensText input tokens
Run

Distilled open-weights model for fast image generation and editing

$0.003/ image512×512 · steps 16
Run

Lighter Nano Banana 2 image model for faster generation and editing workflows

$0.033603/ imageExample: 1K image output
Run

Realtime audio generation

View all

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

$0.000035/ character
Run

Flagship multilingual text-to-speech with natural language voice control and realtime streaming

$0.000015/ UTF-8 byte
Run

Faster HeyGen text-to-speech with public voices and instant voice cloning

$0.000004/ character
Run

Prompt enhancement

View all

Instruction-tuned language model optimized for prompt enhancement and rewriting

—
Run

Open-weight alternatives

Black Forest Labs

FLUX 3 Image Klein Base

by Black Forest Labs

Undistilled open-weights foundation for fine-tuning and customization

$0.0089 / image · 512×512 · steps 50
K

Krea 2 Turbo

by krea

Fast open-source Krea image model for low-cost text-to-image generation and LoRA-friendly workflows

$0.015 / image
K

Krea 2 Raw

by krea

Base 12B Krea 2 checkpoint for finetuning, post-training, and open-weight text-to-image workflows

$0.015 / image
RunDiffusion

Juggernaut Z

by RunDiffusion

Polished image model with stronger cinematic lighting, cleaner focus, and richer portrait detail

$0.01495 / image · 1024 x 1024

Model guides

GPT-Image-2.5 Flare

Prompting

How to prompt GPT-Image-2.5 Flare: writing a brief it can plan a layout from, pinning counts and positions, and choosing a size from its custom dimension envelope.

Read the guide →
GPT-Image-2.5 Flare

Quality levels

How to set rendering effort on GPT-Image-2.5 Flare with settings.quality: what each level changes, what it costs, and which subjects are worth the top of the ladder.

Read the guide →
GPT-Image-2.5 Flare

Editing images

How to edit an image with GPT-Image-2.5 Flare: one source, one written instruction, and the composition, lighting and detail the model holds while it changes what you named.

Read the guide →
GPT-Image-2.5 Flare

Subject consistency

How to keep one product or character recognisable across new scenes with GPT-Image-2.5 Flare: how many reference images to send, and how to say what each one is for.

Read the guide →
GPT-Image-2.5 Flare

Masked editing

How to confine an edit to a painted region with GPT-Image-2.5 Flare: what white and black mean, and why the mask is guidance rather than a hard boundary.

Read the guide →
GPT-Image-2.5 Flare

Iterative editing

How to run a chain of edits with GPT-Image-2.5 Flare: feeding each result back as the next source, what accumulates across passes, and when to restate instead of chain.

Read the guide →
GPT-Image-2.5 Flare

Transparent backgrounds

How to generate cut-out assets with GPT-Image-2.5 Flare: settings.background, the output format it forces, and prompting for edges that survive compositing.

Read the guide →
FLUX 3 Image Klein

Prompting

How to prompt FLUX 3 Image Klein for text-to-image: writing a full scene caption, holding a layout with the seed, sizing up to 4K, and trading steps for speed.

Read the guide →
FLUX 3 Image Klein

Rendering text

How to render readable text with FLUX 3 Image Klein: quoting the exact words, controlling the text you didn't ask for, building a layout hierarchy, and editing signage.

Read the guide →
FLUX 3 Image Klein

Editing images

How to edit a photo with FLUX 3 Image Klein: scoping the change, removing objects, writing scene-wide edits as captions, reframing, and chaining edits.

Read the guide →
FLUX 3 Image Klein

Multi-reference composition

How to combine up to four references with FLUX 3 Image Klein: assigning roles, keeping a product across scenes, placing it in your own photo, and borrowing a style.

Read the guide →
FLUX 3 Image Klein

Bounding boxes

How to place, move and remove elements by region with FLUX 3 Image Klein: the 0 to 1000 grid, laying out a frame, reserving space for copy, and editing by box.

Read the guide →
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 →
Fish Audio S2.1 Pro

Emotion and expression control

How to control vocal delivery in Fish Audio S2-Pro with bracket tags. The tag system steers emotion, expression, paralanguage, and phoneme-level pronunciation in one inline syntax.

Read the guide →
Fish Audio S2.1 Pro

Multi-speaker dialogue

How to generate two-speaker dialogue audio in a single request to Fish Audio S2-Pro using inline speaker tags. One call, two voices, full per-speaker emotion control.

Read the guide →