TollNode

P-Video Avatar API and MCP for AI agents

TollNode gives Claude, Cursor or any AI agent P-Video Avatar, Pruna AI's model that turns one portrait into a lip-synced talking video, over API and MCP, from $0.339 per video up to 10 seconds, with no subscription.

Send one portrait and a script and get a talking video back, with the voice and lip sync done.

No subscription · Sign-up optional · From $0.339 per call · Charged only when it works · No Pruna AI account needed

Claude Code

Make a talking video from this portrait: 'Hi, I'm your new presenter.'

TollNode · Pruna AI · 10$0.339 · 1 talking video

ResultDetail
File1 video link
Lengthup to 10 seconds

Real result, shown below.

Works in Claude Code, Cursor, Codex, VS Code and any MCP agent.

P-Video Avatar examples

Made by this node in our own tests, from the request shown under each.

AI-generatedvoice_script: Hi, I'm your new presenter. Send me a script, and I'll say it on camera in seconds.max_seconds: 10

The request that made it

Send the same body to get this kind of result. Change the prompt or the options to get your own.

request body
{
  "image": "https://tollnode.com/examples/video-p-video-avatar.jpg",
  "voice_script": "Hi, I'm your new presenter. Send me a script, and I'll say it on camera in seconds.",
  "max_seconds": 10
}

What you control with P-Video Avatar

Failed calls are never charged.

What people ask their AI to do with it

Use it as a P-Video Avatar MCP server in Claude, Cursor or Codex

Connect once. Then just ask.

Paste this into Claude Code, Cursor or Codex. It connects TollNode and gives your agent a small wallet. Add a few dollars of USDC and you're done.

terminal
npx agentcash add https://tollnode.com

Copy for your AI agent

Paste this into your agent so it knows what this node does and how to call it.

prompt
You can use TollNode's P-Video Avatar node to make a video. Call POST https://tollnode.com/api/v1/nodes/video-p-video-avatar with audio (optional), image (required), voice (optional), max_seconds (optional), video_prompt (optional), voice_prompt (optional). The price depends on max_seconds (10, 20; default 10) and is charged only when a result is returned. Over MCP, call the "video-p-video-avatar" tool; use list_models to see prices. Give me the file link when it is done.

Price

from $0.034

per second

One call: from $0.339 per video up to 10 seconds

The price depends on the max_seconds you choose. If you don't choose, you get up to 10 seconds.

up to 10 secondsdefault$0.339 per video up to 10 seconds
up to 20 seconds$0.676 per video up to 20 seconds

Charged only when a call returns a result. Failed or empty calls cost $0.

P-Video Avatar without a Pruna AI account

FAQ

Is this the official Pruna AI API?
No. TollNode is an independent service. It gives your agent access to P-Video Avatar through its own API and MCP server, priced per video, with no Pruna AI account needed.
Can I use it as a P-Video Avatar MCP server in Claude?
Yes. Add https://tollnode.com/mcp in Claude Code, Claude Desktop or Cursor, and the "video-p-video-avatar" tool appears with its options and prices.
What options can I choose?
The length can be up to 10 seconds or up to 20 seconds; the default is up to 10 seconds. The price follows the option you pick, shown in the price table above.
How long can the video be?
Up to 20 seconds. Set max_seconds to 10 or 20; longer audio or scripts are refused before anything runs and are not charged.
Do I need my own recording?
No. Send your own MP3 or WAV in audio, or send a script in voice_script and pick a voice. The video is as long as the speech.
What if nothing comes back?
You're not charged. TollNode only collects payment when a usable result is returned.
How long are the links valid?
Download the file when you get it. Keep the link as a backup.

Ready in a minute

Connect your AI
For developers: endpoint, inputs and an example response

POST https://tollnode.com/api/v1/nodes/video-p-video-avatar

Input

FieldTypeNotes
seedinteger
audiostringYour own speech as an MP3 or WAV URL; the video is as long as the audio. Use this or voice_script. Or send the file inline as a base64 data: URI (up to 4.5 MB)
image*stringPortrait of the person who speaks, the first frame (https URL, jpg, png or webp). Or send the file inline as a base64 data: URI (up to 4.5 MB)
voiceenumVoice for voice_script. Default Zephyr (Female) (Zephyr (Female), Puck (Male), Charon (Male), Kore (Female), Fenrir (Male), Leda (Female), Orus (Male), Aoede (Female), Callirrhoe (Female), Autonoe (Female), Enceladus (Male), Iapetus (Male), Umbriel (Male), Algenib (Male), Despina (Female), Erinome (Female), Laomedeia (Female), Achernar (Female), Algieba (Male), Schedar (Male), Gacrux (Female), Pulcherrima (Female), Achird (Male), Zubenelgenubi (Male), Vindemiatrix (Female), Sadachbia (Male), Sadaltager (Male), Sulafat (Female), Alnilam (Male), Rasalgethi (Male))
max_secondsenumLongest the video can be; sets the price. Longer audio or scripts are refused before anything runs, and not charged. Default 10 (10, 20)
video_promptstringHow the person looks and moves while speaking
voice_promptstringHow to say it: tone, pace, accent
voice_scriptstringExact words to say, spoken by the chosen voice, when you send no audio (about 2.3 words a second)
voice_languageenumLanguage of voice_script. Default English (US) (English (US), English (UK), Spanish, French, German, Italian, Portuguese (Brazil), Japanese, Korean, Hindi)
negative_promptstringWhat you do not want, e.g. subtitles or text

Example response

{
  "videos": [
    "https://tollnode.com/api/v1/files/00000000-0000-0000-0000-000000000000/0"
  ],
  "aiGenerated": true
}

Also described in the OpenAPI file and llms.txt. Setup for every app: Agents & MCP.