Use cases · Faceless channels
Faceless videos, made by the batch
Script, b-roll, voiceover and captions for faceless YouTube channels, from one account. Each video has a cost you can read before you run it, and the whole pipeline runs from Claude Code or your own code.
From $1.37 per piece at current prices
What you can make
- 30 to 60 second vertical Shorts with b-roll, voiceover and captions
- Long narrated videos built on still images, documentary or list style
- Scenery and ambient clips for relaxation or music channels
- The same video in other languages with dubbing
- Thumbnails and channel art from the same image models
The pipeline
- 1
Script
One script run turns a topic into a hook, a narration and a shot list.
- 2
Voice
ElevenLabs reads the narration. One block covers about 450 characters, roughly 30 seconds of speech.
- 3
B-roll
Seedance fast renders each shot as a 5 second clip. For long videos, Seedream 4.0 stills cost less; Kling v3 or Hailuo 02 when a shot needs more motion.
- 4
Captions and export
Captions are timed to the voice, and the export stitches clips, voice and text into a 9:16 or 16:9 file.
Cost per piece
Each line is a real row of the rate table at the public prepaid price, multiplied out. A range means the price depends on something only the run decides, such as the length of the text. Each job shows what it actually cost.
A 30 second faceless Short
Six 5 second b-roll clips and one voice block.
A 10 minute narrated video on stills
About 1,500 words of narration over 40 images.
Every rate, machine-readable: GET /api/pricing
Run it from Claude Code
Connect the hosted MCP server once, then describe the batch in plain words. Claude plans it, calls the models, waits for each render and hands you the files with what they cost.
claude mcp add --transport http aitachyon \
https://aitachyon.com/api/mcp \
--header "Authorization: Bearer ait_..."“Make five 30 second faceless Shorts about unsolved mysteries of the sea: write the scripts, voice them with a calm ElevenLabs narrator, six Seedance fast b-roll clips each, burned-in captions, 9:16. Tell me the total cost before you start.”
Or from your code
Plain HTTP with a bearer key. Video returns a job you poll; every file carries a ref you can fetch later with GET /api/generations/{ref}.
curl https://aitachyon.com/api/scenes/generate \
-H "Authorization: Bearer ait_your_key" \
-H "Content-Type: application/json" \
-d '{"projectId":"<project id>","prompt":"Slow aerial shot over a foggy pine forest at dawn","engine":"seedance","mode":"fast","ratio":"9:16","duration":5}'curl https://aitachyon.com/api/voiceover/generate \
-H "Authorization: Bearer ait_your_key" \
-H "Content-Type: application/json" \
-d '{"projectId":"<project id>","provider":"elevenlabs","voiceId":"<from GET /api/voiceover/voices>","text":"Nobody knows who built this road. Here is what we found."}'Built for volume
- Pay per call from a prepaid dollar balance that never expires
- A failed render is refunded to your balance automatically
- Per-key spend, alerts and one-click revoke, so a runaway script stays contained
- Every file has a ref you can fetch with GET /api/generations/{ref}
- The web studio, the HTTP API and the MCP server share one account and one balance
Platform rules you need to respect
Generating is the easy part. What you publish is your responsibility, and each platform has rules for AI content. Never present an AI person as a real customer, a real review or a real event.
YouTube
Monetized channels are reviewed for inauthentic content: mass-produced or repetitive videos without real value added. Realistic altered or synthetic content has to be disclosed when you upload.
TikTok
Realistic AI-generated content has to carry a label, set with the AI-generated content toggle when you post. TikTok may also label it automatically.
Meta (Facebook, Instagram)
Meta labels content it detects as AI-made and asks you to disclose photorealistic video and realistic audio created or altered with AI. Ads about social issues, elections or politics have their own disclosure rules.
Policies change: read the current version before you publish. We make the files; we do not promise monetization, reach or views.