HERMES + VEO 3

Use Veo 3 in Hermes Agent.

Veo 3 is Google DeepMind's video generation model that produces 1080p clips up to 8 seconds with native audio — synchronized dialogue, ambient sound, and music generated alongside the video. Hermes Agent calls it through the RunAPI custom provider endpoint, reusing the same API key configured for chat.

one API key · text to video endpoint · native audio output
Generate a cinematic video clip with native audio using Google Veo 3 through RunAPI.

Requirements:
- Read the API key from RUNAPI_API_KEY. Do not hardcode the key.
- Use the custom:runapi provider with base_url https://runapi.ai/v1.
- Send a POST request to https://runapi.ai/api/v1/veo_3_1/text_to_video
- Set model to "veo-3.1".
- Write a descriptive prompt including scene, camera movement, and audio cues.
- Set duration_seconds to 4, 6, or 8.
- Set aspect_ratio to "16:9", "9:16", or "auto".
- The task is async. Poll the returned task_id until status is "completed".
- When done, read the video URL from the response output.
curl -X POST https://runapi.ai/api/v1/veo_3_1/text_to_video \
  -H "Authorization: Bearer $RUNAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "veo-3.1",
    "prompt": "A woman walks through a bustling Tokyo street at night, neon signs reflecting on wet pavement. She speaks into her phone: I just arrived. Ambient city noise, distant car horns, light rain.",
    "duration_seconds": 8,
    "aspect_ratio": "16:9"
  }'
{
  "task_id": "tsk_abc123",
  "status": "pending",
  "model": "veo-3.1"
}
Copy the curl command to test veo-3
HOW IT WORKS

Use Veo 3 in Hermes Agent in three steps

1

Configure RunAPI

Set RUNAPI_API_KEY in the environment where Hermes Agent runs. If you already added RunAPI as a custom:runapi provider for chat, the same key and base_url handle video generation — no separate Google Cloud credentials needed.

export RUNAPI_API_KEY=runapi_xxx
2

Call Veo 3 text_to_video

Send a POST to the text_to_video endpoint with model set to veo-3.1. Include a prompt with scene descriptions and audio cues (dialogue, ambient sounds). Set duration_seconds to 4, 6, or 8 and aspect_ratio to 16:9 or 9:16. Hermes Agent routes through the custom:runapi provider.

POST /api/v1/veo_3_1/text_to_video
3

Poll for the result

The endpoint returns a task_id immediately. Poll the task status endpoint until the status changes to completed, then retrieve the output video URL. The video includes synchronized audio generated from your prompt.

GET /api/v1/veo_3_1/text_to_video/tsk_abc123
PARAMETERS

Veo 3 text_to_video parameters

Parameter Type Description
model string Required. veo-3.1 (standard quality) or veo-3.1-fast (lower cost, faster generation).
prompt string Required. Scene description including visual action, camera movement, and audio cues for dialogue or ambient sound.
duration_seconds integer Optional. Video length in seconds. Accepted values: 4, 6, 8. Defaults to 8.
aspect_ratio string Optional. Output aspect ratio. Accepted values: 16:9, 9:16, auto.
input_mode string Optional. Generation mode. text (default), first_and_last_frames (keyframe-guided), or reference (style reference).
first_frame_image_url string Optional. URL of the first frame image. Used when input_mode is first_and_last_frames.
last_frame_image_url string Optional. URL of the last frame image. Used when input_mode is first_and_last_frames.
reference_image_urls array Optional. URLs of style reference images. Used when input_mode is reference.
callback_url string Optional. Webhook URL that receives a POST when the task completes.

What is Veo 3 on Hermes Agent?

Veo 3 from Google DeepMind creates video that feels alive -- cinematic visuals with synchronized dialogue, ambient sound, and music generated together in one pass. Through the Hermes Agent custom:runapi provider, you get 1080p clips up to 8 seconds with native audio, so there is no separate TTS or sound editing step required.

Veo 3 use cases

Anime and stylized sequences

Generate anime-style or stylized video clips with matching audio cues. Describe the visual style and sound direction in the prompt and Veo 3 renders both together.

Music and singing content

Create short music video clips or singing duet scenes. Include lyrics or musical direction in the prompt for synchronized audio-visual output.

Social media content with sound

Produce ready-to-post video clips with ambient audio, voiceover, or dialogue built in. No audio editing needed -- the output is complete with both video and sound tracks.

FAQ

Veo 3 + Hermes Agent questions

Hermes Agent general setup

Not configured yet? Start with the RunAPI setup guide for Hermes Agent.

Hermes Agent setup guide →

Veo 3 model catalog

See Veo 3 variants, pricing tiers, and API docs.

Veo 3 on RunAPI →

Try Veo 3 in Hermes Agent today.

Get a free RunAPI key, configure the custom:runapi provider, and generate cinematic video with native audio using Google Veo 3.