Public Versions and Endpoints
| Model ID | Endpoints | Price | Catalog |
|---|---|---|---|
infinitetalk-from-audio
|
/api/v1/infinitetalk/audio_to_video
|
$0.12 / second | Model detail |
Verify
Poll until the task reaches a terminal status
POST /api/v1/infinitetalk/audio_to_video and save the returned Task id.
GET /api/v1/infinitetalk/audio_to_video/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.Configuration
Guide endpoint: /api/v1/infinitetalk/audio_to_video
export RUNAPI_API_KEY=your_api_key
curl -X POST https://runapi.ai/api/v1/infinitetalk/audio_to_video \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "infinitetalk-from-audio",
"source_image_url": "https://file.runapi.ai/portrait.png",
"source_audio_url": "https://file.runapi.ai/narration.mp3",
"prompt": "A natural speaking portrait."
}'Get Started in 3 Steps
-
Choose a model ID
Select a public catalog model ID and review its endpoint and current starting price.
-
Configure RunAPI
Set RUNAPI_API_KEY before making the endpoint request.
-
Verify the result
For asynchronous endpoints, poll the same endpoint until the Task reaches a terminal status.
What to Build with Hermes Agent + InfiniteTalk
-
YouTube content with AI presenters
Generate talking-head videos from a single photo for YouTube channels, keeping a consistent presenter across videos without on-camera filming.
-
Video dubbing with lip sync
Animate a presenter to match a new audio track in another language, producing dubbed content where mouth movements follow the translated speech.
-
Long-form lecture and presentation videos
Turn recorded narration and one instructor photo into talking avatar videos for online courses, webinars, or internal training.
Why Use InfiniteTalk Through RunAPI + Hermes Agent
-
1 variants, one API key
Use one RunAPI connection to choose among the live model variants without changing your integration.
-
Clear usage pricing
See current catalog pricing before you send a request, with no subscription or minimum spend required.
-
Automatic task workflows
Submit, poll, and collect asynchronous results through a consistent task workflow without writing manual polling code.
Hermes Agent + InfiniteTalk Questions
Can I use InfiniteTalk in Hermes Agent?
Yes. With RunAPI configured as a provider in Hermes Agent, the agent can submit InfiniteTalk tasks with an audio file and a reference image using your RunAPI API key.
How long can an InfiniteTalk video be?
The output length follows the source audio. InfiniteTalk animates the reference image for the full duration of the speech track you provide.
Can I chain InfiniteTalk with other models in a Hermes Agent workflow?
Yes. Hermes Agent can generate speech with a text-to-speech model first, then pass the audio URL to InfiniteTalk to produce the avatar video in the same run.
Which model ID should I use?
Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version.
Does this guide configure a chat model?
No. This Model Line uses the endpoint workflow shown here and is not presented as an agent chat model.