How to Use Hedra Character 3 in Muse
Hedra Character 3 turns a portrait and recorded speech or singing into a lip-synced video. Use it for seated presenters, lessons, and character narration, with restrained movement directions.
Prompts to try with Hedra Character 3 in Muse
Copy an example into Muse, or ask in your own words.
Use Hedra Character 3 to animate this presenter portrait with my 20-second announcement recording. Make it 720p, with hands resting, small head movements, and a stationary camera.
Use Hedra Character 3 with this teacher portrait and my 25-second explanation. Create a 720p lesson clip with patient delivery and limited body movement.
Use Hedra Character 3 to turn this illustrated host and 15-second spoken excerpt into a 720p podcast clip. Keep the host seated and the delivery conversational.
Use Hedra Character 3 with this narrator portrait and 30-second bedtime-story recording. Make a 720p video with gentle delivery, slow head movement, and still framing.
Use Hedra Character 3 to animate this clay character with my 12-second singing recording at 720p. Keep the character seated with gentle head movement.
How to set up Hedra Character 3 in Muse
Pick the way that suits you. Each takes about two minutes.
Use the Muse connector
- Create an API key
Create one under API keys in the Spiral console.
- Send Muse this message
Muse reads Spiral's skill and asks for an API key.
set up https://spiral.ai/SKILL.md
- Give Muse the key
Paste the key when Muse asks for it, never in the chat itself.
Use the Spiral skill
- Send Muse this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Hedra Character 3
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "hedra", "model": "hedra-character-3", "input": { "audio": { "url": "<url>", "source": "url" }, "prompt": "Generate a realistic talking avatar video with lip sync", "resolution": "720p", "start_image": { "url": "<url>", "source": "url" }, "aspect_ratio": "9:16" } }'
Then paste one of the prompts above: Muse finds Hedra Character 3 on Spiral, shows the price and runs it.
Hedra Character 3 providers and prices
Spiral runs Hedra Character 3 through Hedra. Open a card for today's price, with every fee included.
$0.065 per second at 720p ($0.0325 at 540p, $0.0813 at 1080p), for the audio's length.
Settings you can ask for
Hedra Character 3 works from your prompt. Ask Muse for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Resolution | 540p, 720p, or 1080p | 720p | Output resolution. |
| Aspect ratio | 1:1, 4:3, 3:4, 16:9, 9:16, 9:21, or 21:9 | 9:16 | Output aspect ratio. |
| Duration ms | a whole number up to 600000 | Duration in ms. At most 600000. |
Every API field of Hedra Character-3 · Talking Avatar Video is on its tool page: open its card above.
What can you do with Hedra Character 3 in Muse?
Bring an attached portrait and recording to life as a talking or singing character. A chat app can help shape the delivery brief for Hedra Character 3, including calm posture and restrained gestures.
Short teaching videos
Animate a teacher portrait with a recorded explanation of one concept. Use patient delivery, resting hands, and a stationary camera.
Character-led product announcements
Turn a character portrait and an approved launch recording into a seated presenter clip for a product announcement.
Animated podcast excerpts
Pair an illustrated host portrait with a short spoken excerpt to make a talking podcast clip.
Bedtime storytelling
Animate a narrator portrait with a gentle story recording. Request still framing and slow, subtle head movement.
Singing character clips
Give a claymation character portrait a short vocal performance using a recorded song excerpt.
News-style briefings
Animate an anchor portrait with a recorded bulletin, using seated posture and restrained gestures.
Localized presenter videos
Create talking presenter clips from an approved portrait and separate narration recordings in the intended languages.
More on Hedra Character 3 and Muse
Overview
Hedra Character 3 in other agents
Questions about Hedra Character 3 in Muse
Can Muse use Hedra Character 3?
Yes. Add Spiral to Muse as an MCP server, and Muse can find and run Hedra Character 3 like any built-in tool.
How much does Hedra Character 3 cost in Muse?
$0.065 per second at 720p ($0.0325 at 540p, $0.0813 at 1080p), for the audio's length. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse plan is separate.
Do I need a Hedra account to use Hedra Character 3 in Muse?
You need no Hedra account. Muse uses one Spiral API key for every tool, and Spiral runs Hedra Character 3 on its own Hedra account.
How long does it take to set up Hedra Character 3 in Muse?
About two minutes: create an API key, then send Muse this message, then give Muse the key.
Does Muse wait while Hedra Character 3 runs?
Hedra Character 3 runs in the background. Muse starts the run, checks on it and gives you the video when it's ready.
What is Hedra Character 3 best at?
Hedra Character 3 is a good fit for seated talking heads: teachers, presenters, narrators, and podcast hosts. Its examples emphasize speech delivery with limited body movement.
How long can Hedra Character 3 videos be, and what resolutions are listed?
Hedra advertises a maximum duration of 10 minutes and lists 540p, 720p, and 1080p output. Those headline specifications do not establish that every resolution supports the full maximum duration.
Does Hedra Character 3 support languages other than English?
Hedra advertises multilingual support for talking and singing videos. Use narration recorded in the intended language.
How should I prompt movement in Hedra Character 3?
Describe the performance directly: seated posture, hands resting, small head movements, and a stationary camera. Hedra uses these directions in its own teacher example.
What can make Hedra Character 3 results look unnatural?
Hedra flags exaggerated hand gestures as a known quirk and recommends explicitly restraining movement in the prompt. It also recommends clearly pronounced speech without background noise or heavy reverb.
Start using Hedra Character 3 in Muse
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Muse:
set up https://spiral.ai/SKILL.md


