How to generate video with audio through an API

To generate video with audio through the RelayDance API, send a POST request to /v1/video/generations with a model, prompt, seconds, and set metadata.generate_audio to true. The API is OpenAI-compatible, so you set your base URL to https://relaydance.com/v1. Then poll GET /v1/video/generations/{task_id} until the status is succeeded, and the result contains the video URL with audio included.

How do you submit a video generation request?

You submit a video task by sending a POST request to /v1/video/generations with the required parameters. Include a model (for example ByteDance Seedance 2.0), a prompt, the number of seconds, and a metadata object. Inside metadata you can set ratio, resolution, generate_audio, callback_url, and content[] for reference media. Authentication uses an Authorization: Bearer YOUR_API_KEY header, and keys are created at the RelayDance console. Because the service is OpenAI-compatible, existing SDKs work directly. As the official docs state, 「Set base_url to https://relaydance.com/v1 and keep your OpenAI SDK」, 据 relaydance.com/docs 官方文档. Clips can run up to 15 seconds per request.

How do you retrieve the finished video?

You retrieve the result by polling GET /v1/video/generations/{task_id} until the status is succeeded or failed. The response for a succeeded task contains the video URL. Alternatively, use webhook mode by setting metadata.callback_url, and the final state is POSTed to your server when the task completes. This removes the need for repeated polling. For reference-based generation, media go in metadata.content[] and are cited in the prompt as @image1 to @imageN. Each request supports up to 9 reference images, 3 reference videos, and 3 audio tracks. See https://relaydance.com/docs for the full request and response schema, including polling intervals and status values.

What does video generation cost?

Billing is pay-as-you-go per generated video, priced per second or per clip depending on the model. Failed requests carry no charge: 「Failed or errored requests are never billed」, 据 relaydance.com 官方文档. Live per-model rates are listed at https://relaydance.com/models.

What are the steps to generate video with audio?

You follow five steps, from key creation to result retrieval, using standard OpenAI-compatible calls.

1. Create an API key at the RelayDance console and set Authorization: Bearer YOUR_API_KEY.
2. Set your base URL to https://relaydance.com/v1 in your OpenAI SDK.
3. POST to /v1/video/generations with model, prompt, seconds, and metadata.generate_audio set to true.
4. Poll GET /v1/video/generations/{task_id}, or set metadata.callback_url for webhook delivery.
5. Read the video URL from the succeeded response.

Reference media (up to 9 images, 3 videos, and 3 audio tracks) can be added via metadata.content[], and clips run up to 15 seconds.

FAQ

Do I need a BytePlus enterprise account or KYC? No. RelayDance provides direct OpenAI-compatible access to Seedance with no BytePlus enterprise account or KYC required.

Am I charged if a request fails? No. According to relaydance.com, 「Failed or errored requests are never billed」.

What payment methods are accepted? Payments are supported through USDT and Stripe card, on a pay-as-you-go basis per generated video.