Find your landing page message
Connect a product’s value to a specific audience and write a clear first-screen message.
Generate videos through public reAPI APIs using VEO 3.1 models such as veo3.1-fast and veo3.1-quality. Requires REAPI_API_KEY or REAPI_KEY from https://reapi.ai.
---
name: veo-3-1
description: "Generate videos through public reAPI APIs using VEO 3.1 models such as veo3.1-fast and veo3.1-quality. Requires REAPI_API_KEY or REAPI_KEY from https://reapi.ai."
---
# VEO 3.1 via reAPI
Generate videos with reAPI using VEO 3.1 model IDs.
This skill is a thin public API wrapper around reAPI. It is not an official
model-provider plugin. Submit only canonical reAPI `model` values documented at
`https://reapi.ai/docs`.
## Configuration
Required:
- `REAPI_API_KEY` or `REAPI_KEY`: reAPI bearer token.
Get an API key:
1. Open `https://reapi.ai`.
2. Sign in or create an account.
3. Go to Dashboard -> API Keys.
4. Create a new key and copy it once.
5. Set it before using the skill:
```bash
export REAPI_API_KEY="rk_live_xxx"
```
Optional:
- `REAPI_BASE_URL`: override the API base URL. Defaults to `https://reapi.ai`.
Never paste or print the user's API key in final answers.
## Model Mapping
Default model:
```text
veo3.1-fast
```
Supported canonical reAPI model IDs:
- `veo3.1-fast`
- `veo3.1-quality`
- `veo3.1-lite`
- `veo3.1-fast-official`
- `veo3.1-quality-official`
Notes:
- Default canonical model ID: `veo3.1-fast`.
- Use `veo3.1-quality` when the user explicitly prefers quality over speed.
- Common fields vary by channel; check the public docs before advanced fields such as first/last frame, seed, sample count, audio, resize mode, or source task ID.
## Quick Start
Check configuration:
```bash
python3 scripts/reapi_model.py config
```
Print supported model IDs:
```bash
python3 scripts/reapi_model.py models
```
Print an example payload:
```bash
python3 scripts/reapi_model.py example
```
Submit a task and wait for completion:
```bash
python3 scripts/reapi_model.py submit --wait --prompt "a drone shot over a futuristic coastal city" --set aspect_ratio=16:9
```
Submit a complete public API payload:
```bash
python3 scripts/reapi_model.py submit --wait --json '{"model":"veo3.1-fast","prompt":"your prompt"}'
```
Poll an existing task:
```bash
python3 scripts/reapi_model.py wait task_xxx
```
Get a task once:
```bash
python3 scripts/reapi_model.py get task_xxx
```
## API Workflow
1. Submit to the public reAPI `videos` generation endpoint.
2. Read `id` from the response.
3. Poll `GET /api/v1/tasks/{id}` every 2-3 seconds.
4. On `status: "completed"`, return URLs from `output.video_urls`.
5. On `status: "failed"`, report the task `error.code` and `error.message`.
Polling does not consume credits. Submission requests consume credits based on
model and parameters.
## References
- `model.json`: machine-readable model mapping used by the CLI.
- `references/MODEL.md`: public model notes for this skill.
- Public docs: `https://reapi.ai/docs/veo3-1`
---
name: veo-3-1
description: "Generate videos through public reAPI APIs using VEO 3.1 models such as veo3.1-fast and veo3.1-quality. Requires REAPI_API_KEY or REAPI_KEY from https://reapi.ai."
---
# VEO 3.1 via reAPI
Generate videos with reAPI using VEO 3.1 model IDs.
This skill is a thin public API wrapper around reAPI. It is not an official
model-provider plugin. Submit only canonical reAPI `model` values documented at
`https://reapi.ai/docs`.
## Configuration
Required:
- `REAPI_API_KEY` or `REAPI_KEY`: reAPI bearer token.
Get an API key:
1. Open `https://reapi.ai`.
2. Sign in or create an account.
3. Go to Dashboard -> API Keys.
4. Create a new key and copy it once.
5. Set it before using the skill:
```bash
export REAPI_API_KEY="rk_live_xxx"
```
Optional:
- `REAPI_BASE_URL`: override the API base URL. Defaults to `https://reapi.ai`.
Never paste or print the user's API key in final answers.
## Model Mapping
Default model:
```text
veo3.1-fast
```
Supported canonical reAPI model IDs:
- `veo3.1-fast`
- `veo3.1-quality`
- `veo3.1-lite`
- `veo3.1-fast-official`
- `veo3.1-quality-official`
Notes:
- Default canonical model ID: `veo3.1-fast`.
- Use `veo3.1-quality` when the user explicitly prefers quality over speed.
- Common fields vary by channel; check the public docs before advanced fields such as first/last frame, seed, sample count, audio, resize mode, or source task ID.
## Quick Start
Check configuration:
```bash
python3 scripts/reapi_model.py config
```
Print supported model IDs:
```bash
python3 scripts/reapi_model.py models
```
Print an example payload:
```bash
python3 scripts/reapi_model.py example
```
Submit a task and wait for completion:
```bash
python3 scripts/reapi_model.py submit --wait --prompt "a drone shot over a futuristic coastal city" --set aspect_ratio=16:9
```
Submit a complete public API payload:
```bash
python3 scripts/reapi_model.py submit --wait --json '{"model":"veo3.1-fast","prompt":"your prompt"}'
```
Poll an existing task:
```bash
python3 scripts/reapi_model.py wait task_xxx
```
Get a task once:
```bash
python3 scripts/reapi_model.py get task_xxx
```
## API Workflow
1. Submit to the public reAPI `videos` generation endpoint.
2. Read `id` from the response.
3. Poll `GET /api/v1/tasks/{id}` every 2-3 seconds.
4. On `status: "completed"`, return URLs from `output.video_urls`.
5. On `status: "failed"`, report the task `error.code` and `error.message`.
Polling does not consume credits. Submission requests consume credits based on
model and parameters.
## References
- `model.json`: machine-readable model mapping used by the CLI.
- `references/MODEL.md`: public model notes for this skill.
- Public docs: `https://reapi.ai/docs/veo3-1`
Imported from the listed AgentSkill.sh category. Complete supplied package files and notices are retained. Includes source scripts; review them before use. Required external tools and credentials are not installed. No bundled code was executed during import. Individual agent task behavior has not been tested.