[Integrations](https://spiral.ai/integrations) › [Perplexity](https://spiral.ai/integrations/perplexity) › [InfiniteTalk Video to Video](https://spiral.ai/integrations/perplexity/infinitetalk-video-to-video)

# How to Use InfiniteTalk Video to Video in Perplexity

InfiniteTalk Video to Video adapts existing presenter footage to new speech or singing, including head and body motion. Unlike InfiniteTalk Image to Video, it references filmed movement, though subtle camera motion may change.

|  |  |
| --- | --- |
| Model | InfiniteTalk Video to Video |
| Available through | WaveSpeed |
| Category | Video |
| Price | $0.039 per second at 480p ($0.078 at 720p), 3 to 600 seconds. |
| Returns | video |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with InfiniteTalk Video to Video in Perplexity

- Use InfiniteTalk Video to Video to adapt the supplied presenter footage to my revised 45-second narration at 720p. Help me compare the resulting gestures and camera movement with the original.
- Use InfiniteTalk Video to Video with this presenter footage and my 30-second FAQ recording. Make a 480p preview with a composed delivery, then help me review lip timing and expressions.
- Make a talking-head video with InfiniteTalk Video to Video from this headshot and this 20-second voiceover.
- Create a 15-second founder intro with InfiniteTalk Video to Video using the photo and script I attach.
- Turn this audio clip into a lip-synced avatar video with InfiniteTalk Video to Video.

## How to set up InfiniteTalk Video to Video in Perplexity

Pick the way that suits you. Each takes about two minutes.

### Use the Perplexity connector

1. **Add a remote connector**: In Perplexity, open Plugins in the sidebar (or Customize › Connectors if you don't see Plugins yet). Choose Add custom › Add MCP connector, then Remote. Name it Spiral and paste this MCP server URL:

```text
https://api.spiral.ai/mcp
```

2. **Sign in to Spiral and approve**: Select the Spiral card on the Plugins page to start sign-in. Spiral opens: sign in, pick the organization and click Authorize. No API key.

### Use the Spiral skill

1. **Send Perplexity this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run InfiniteTalk Video to Video**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "wavespeed",
    "model": "wavespeed-ai/infinitetalk/video-to-video",
    "input": {
      "audio": "<audio>",
      "video": "<video>"
    }
  }'
```

Then paste one of the prompts above: Perplexity finds InfiniteTalk Video to Video on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/perplexity

## InfiniteTalk Video to Video tools and prices

- [InfiniteTalk Lip-sync · Video to Video](https://spiral.ai/tools/wavespeed/wavespeed-ai/infinitetalk/video-to-video) (WaveSpeed): $0.039 per second at 480p ($0.078 at 720p), 3 to 600 seconds.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — | The random seed to use for the generation. -1 means a random seed will be used. |
| prompt |  | — | The positive prompt for the generation. |
| mask_image |  | — | Optional mask image to specify the person in the video to animate. |
| resolution | 480p, 720p | 480p | The resolution of the output video. |

## What can you do with InfiniteTalk Video to Video in Perplexity?

Turn recorded explanations into presenter videos you can review in conversation. Ask the agent to keep each request focused on one delivery style and check the result against the supplied audio.

### Short training lessons

Create 30- to 60-second presenter clips that accompany recorded instructions, with facial expressions and gestures following the narration.

### Product announcements

Turn an approved announcement recording into a short presenter video for a product update or release recap.

### Spoken FAQ clips

Make a separate presenter video for each recorded answer so individual explanations can be reviewed and replaced.

### Singing previews

Pair a short vocal recording with a visible performer to preview lip movement and expression before editing a longer music video.

### Revised presenter narration

Adapt existing presenter footage to an updated recording. Review regenerated gestures and camera movement against the original.

### Dubbed presenter footage

Adapt filmed delivery to a replacement spoken performance, allowing facial and body movements to follow the new audio.

## Overview

- [WaveSpeed AI](https://spiral.ai/providers/wavespeed)
- [All Perplexity guides](https://spiral.ai/integrations/perplexity)

## InfiniteTalk Video to Video in other agents

- [Amp](https://spiral.ai/integrations/amp/infinitetalk-video-to-video)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/infinitetalk-video-to-video)
- [Claude](https://spiral.ai/integrations/claude-desktop/infinitetalk-video-to-video)
- [Claude Code](https://spiral.ai/integrations/claude-code/infinitetalk-video-to-video)
- [Cline](https://spiral.ai/integrations/cline/infinitetalk-video-to-video)
- [Codex](https://spiral.ai/integrations/codex/infinitetalk-video-to-video)
- [Cursor](https://spiral.ai/integrations/cursor/infinitetalk-video-to-video)
- [Devin](https://spiral.ai/integrations/devin/infinitetalk-video-to-video)
- [dots](https://spiral.ai/integrations/dots/infinitetalk-video-to-video)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/infinitetalk-video-to-video)
- [Gemini](https://spiral.ai/integrations/gemini/infinitetalk-video-to-video)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/infinitetalk-video-to-video)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/infinitetalk-video-to-video)
- [goose](https://spiral.ai/integrations/goose/infinitetalk-video-to-video)
- [Grok](https://spiral.ai/integrations/grok/infinitetalk-video-to-video)
- [Grok Build](https://spiral.ai/integrations/grok-build/infinitetalk-video-to-video)
- [Hermes](https://spiral.ai/integrations/hermes/infinitetalk-video-to-video)
- [Instinct](https://spiral.ai/integrations/instinct/infinitetalk-video-to-video)
- [Manus](https://spiral.ai/integrations/manus/infinitetalk-video-to-video)
- [Muse](https://spiral.ai/integrations/muse/infinitetalk-video-to-video)
- [Muse Code](https://spiral.ai/integrations/muse-code/infinitetalk-video-to-video)
- [n8n](https://spiral.ai/integrations/n8n/infinitetalk-video-to-video)
- [Notion](https://spiral.ai/integrations/notion/infinitetalk-video-to-video)
- [OpenClaw](https://spiral.ai/integrations/openclaw/infinitetalk-video-to-video)
- [opencode](https://spiral.ai/integrations/opencode/infinitetalk-video-to-video)
- [Raycast](https://spiral.ai/integrations/raycast/infinitetalk-video-to-video)
- [VS Code](https://spiral.ai/integrations/vscode/infinitetalk-video-to-video)
- [Windsurf](https://spiral.ai/integrations/windsurf/infinitetalk-video-to-video)
- [Zapier](https://spiral.ai/integrations/zapier/infinitetalk-video-to-video)

## More Perplexity guides

- [InfiniteTalk Image to Video](https://spiral.ai/integrations/perplexity/infinitetalk-image-to-video)
- [Kandinsky 6.0 Pro Image to Video](https://spiral.ai/integrations/perplexity/kandinsky-6-0-pro-image-to-video)
- [HeyGen Video Translate Speed](https://spiral.ai/integrations/perplexity/heygen-video-translate-speed)
- [Kandinsky 6.0 Pro Text to Video](https://spiral.ai/integrations/perplexity/kandinsky-6-0-pro-text-to-video)
- [HeyGen Video Translate Precision](https://spiral.ai/integrations/perplexity/heygen-video-translate-precision)
- [Kling 1.0 Standard Effects](https://spiral.ai/integrations/perplexity/kling-1-0-standard-effects)

## Questions about InfiniteTalk Video to Video in Perplexity

**Can Perplexity use InfiniteTalk Video to Video?**

Yes. Add Spiral to Perplexity as an MCP server, and Perplexity can find and run InfiniteTalk Video to Video like any built-in tool.

**How much does InfiniteTalk Video to Video cost in Perplexity?**

$0.039 per second at 480p ($0.078 at 720p), 3 to 600 seconds. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Perplexity plan is separate.

**Do I need a WaveSpeed account to use InfiniteTalk Video to Video in Perplexity?**

No. Spiral runs InfiniteTalk Video to Video on its own WaveSpeed account. You sign in to Spiral once and never paste a key.

**How long does it take to set up InfiniteTalk Video to Video in Perplexity?**

About two minutes: add a remote connector, then sign in to Spiral and approve.

**Does Perplexity wait while InfiniteTalk Video to Video runs?**

InfiniteTalk Video to Video runs in the background. Perplexity starts the run, checks on it and gives you the video when it's ready.

**What is InfiniteTalk best at?**

InfiniteTalk makes talking or singing presenter videos whose lips, facial expressions, head movements, and posture follow supplied audio. It suits narration where the speaker's delivery matters visually.

**Does InfiniteTalk change more than the mouth?**

Yes. It also generates head, face, and body motion that follows the audio, so review gestures and expressions along with lip sync.

**How long can an InfiniteTalk video be?**

The documented maximum is 10 minutes per job. Treat that as a length limit, not a guarantee of consistent quality throughout; review longer results before using them.

**What resolution can InfiniteTalk produce?**

InfiniteTalk supports 480p and 720p output. Use a short sample to check facial detail before generating a full narration.

**Can InfiniteTalk animate singing?**

Yes. Both photo animation and video dubbing support singing audio as well as speech.

