AI Tools You Can Use Right Now
Skip the API keys. Skip the install. These AI tools run on my own infrastructure, and you pay per use. No subscriptions, no setup.
Currently in private beta. Contact me to get access or join the waitlist.
Image Generation
What you can do: Text-to-image and image-to-image. High-quality outputs (1024×1024 to 1536×1536), no technical setup.
Models available:
- FLUX.1 Pro — best for photorealism, $0.05 per image
- Stable Diffusion XL — best for artistic styles, $0.02 per image
- Ideogram 2.0 — best for text-in-image (posters, logos), $0.04 per image
Sample use cases: Blog hero images, product mockups, social media graphics, ad creatives.
API access: Coming via REST API. For now, generate via the web form.
Voice Synthesis
What you can do: Text-to-speech with emotional control, voice cloning (with consent), multilingual support.
Models available:
- ElevenLabs Multilingual v2 — 29 languages, emotion control, $0.18 per 1000 characters
- OpenAI TTS HD — 6 voices, reliable, $0.030 per 1000 characters
- Piper TTS — self-hosted option, free for low-volume use
Sample use cases: YouTube narration, podcast intros, explainer videos, e-learning.
Video Generation
What you can do: Text-to-video and image-to-video. Asynchronous generation (queue + email when ready).
Models available:
- Runway Gen-3 Alpha — best quality, 10s clips, $0.50 per second
- Pika 1.5 — best for short social clips, $0.20 per second
- Stable Video Diffusion — open source, 4s clips, $0.10 per second
Sample use cases: Product demos, social ads, B-roll for longer videos, animated explainers.
Note: Video generation takes 2-5 minutes per clip. You’ll get an email when your video is ready.
Music Generation
What you can do: Text-to-music, genre control, instrumental or with vocals.
Models available:
- Suno v4 — best for pop, rock, electronic, $0.10 per song
- Udio 1.5 — best for hip-hop, jazz, classical, $0.10 per song
- Stable Audio 2.0 — best for ambient/background music, $0.05 per 30s clip
Sample use cases: YouTube background music, podcast intros, jingles, custom music for ads.
Note: Generated music is licensed for your use. You own the output.
Pricing
Pay per use. No subscription. Top up your account once, spend it on whatever tool you need.
| Plan | Credit | What you can do | Price |
|---|---|---|---|
| Starter | 100 credits | ~10 images OR ~3 minutes voice OR ~2 minutes video OR ~10 songs | $10 |
| Creator | 500 credits | ~50 images OR ~15 minutes voice OR ~10 minutes video OR ~50 songs | $45 |
| Pro | 2000 credits | ~200 images OR ~60 minutes voice OR ~40 minutes video OR ~200 songs | $160 |
| Business | 10000 credits | Bulk use, custom workflows, dedicated support | $700 |
1 credit ≈ $0.10 of underlying API cost. We mark up 20-30% to cover infrastructure and support.
Credits never expire. Use them whenever you need.
How It Works
- Sign up with your email and pick a plan (or start with the free trial: 10 credits free)
- Choose a tool (image, voice, video, music) and a model
- Submit your request (text prompt, voice script, video storyboard, music description)
- Get results in your dashboard, via email, or via API webhook
- Download in your preferred format (PNG, MP3, MP4, WAV)
API Access
For higher volume or custom integrations, API access is available on the Pro plan and above. REST API with predictable pricing per request.
Documentation: Request access — I’ll send you the API docs and an integration key.
Get Early Access
These tools are in private beta. To get access:
- Email me at xiaofouyang@gmail.com with “AI Tools access” in the subject
- Use the contact form at /contact/
- Include a brief description of what you want to generate (so I can prioritize)
I’ll get back to you within 24 hours with either access or a waitlist position.
Last updated: 2026-06-06 · Pricing and models subject to change as underlying APIs evolve. Credits purchased before any change are honored at the original rate.