Music Bed
Music Bed puts one music track under a finished clip. The clip keeps its own sound. The output has the same length as the clip.
assembly · model music-bed · catalog model-catalog@2026-10-06.v5 · pricing customer-pricing@2026-11-05.v15.Endpoint
POST https://api.roasos.com/v1/assembly/music-bedSend your API key as a bearer token. The key needs the scope api:write. Every paid request also needs an Idempotency-Key header.
The envelope fields quote_only, quote_id, webhook_url and wait_timeout_seconds behave the same on each model endpoint. Refer to Jobs and Quotes and credits.
Good at
Use it to add music below a voice. To replace the sound of a clip, use merge-audio-video.
The price is one credit, flat. The length of the clip does not change the price.
Pricing
The unit is one operation. Pricing key: music-bed.
| Request | Credits |
|---|---|
per_operation | 1 |
The credits come from the roasOS pricing table. No other field changes the price. To get the exact price of your request, send it with quote_only: true first.
Modes
music-bed
Provider endpoints: fal-ai/ffmpeg-api/compose.
Request fields
| Field | Type | Required | Default | Rule |
|---|---|---|---|---|
audio_url | string | yes | — | https URL; ≤ 4,096 characters |
quote_id | string | no | — | UUID |
quote_only | boolean | no | false | — |
speech_spans | object[] | no | — | 1–200 items; each { start_seconds, end_seconds } |
video_url | string | yes | — | https URL; ≤ 4,096 characters |
wait_timeout_seconds | integer | no | 0 | 0–60 |
webhook_url | string | no | — | https URL; ≤ 4,096 characters |
The schema is strict. A field that is not in this table gets 400 unsupported_option. The field names are the roasOS role names. One role has one name in every family.
Media
This endpoint accepts these media roles:
video_url— the source videoaudio_url— the driving audio track
| Role | Items | Maximum size | Content types | Duration |
|---|---|---|---|---|
audio_url | ≤ 1 | 15 MB | audio/mp3, audio/mpeg, audio/wav, audio/wave, audio/x-wav | — |
video_url | ≤ 1 | 100 MB | video/mp4 | 0–180 s |
Every other role is refused: avatar_id, elements, product_id, product_images, references, reference_images, image_url, end_image_url, scene_id, scene_image, video_urls, audio_urls, voice_id. A refused role gets 400 unsupported_option.
https://cdn.roasos.com that your workspace owns. Any other URL gets 400 reference_media_not_workspace_owned. Refer to Reference media and uploads to learn how to put a file there.Prompt
None. This operation takes no prompt.
speech_spans sets the times of the voice, in seconds. The music becomes quieter during each span and louder in the gaps. If you do not send speech_spans, the music stays at one low level.
Send a music file that is at least as long as the clip. If the music is shorter, the end of the clip has no music.
Not exposed
roasOS pins no provider field for this model.
Result
The result kind is video. Always present: url.
{
"data": {
"id": "gen_…",
"kind": "video",
"model": "music-bed",
"status": "completed",
"result": {
"url": "https://cdn.roasos.com/workspaces/ws_01/result"
}
}
}The files are immutable objects on https://cdn.roasos.com. A result URL is a valid media input for your next request.
Example
The three steps are always the same: quote, run, poll.
# 1. Quote. Nothing is spent.
curl -X POST https://api.roasos.com/v1/assembly/music-bed \
-H "Authorization: Bearer roasos_sk_live_..." \
-H "Idempotency-Key: 0f1c9e2a-music-bed-0001" \
-H "Content-Type: application/json" \
-d '{"quote_only":true,"audio_url":"https://cdn.roasos.com/workspaces/ws_01/uploads/audio_url.mp3","video_url":"https://cdn.roasos.com/workspaces/ws_01/uploads/video_url.mp4"}'
# 200 { "data": { "kind": "quote", "quote_id": "q_7Hk...", "credits": 1, "expires_at": "...",
# "confirmation": { "model": "music-bed", "example": "per_operation" } } }
# 2. Run. Same body, same Idempotency-Key, quote_id in place of quote_only.
curl -X POST https://api.roasos.com/v1/assembly/music-bed \
-H "Authorization: Bearer roasos_sk_live_..." \
-H "Idempotency-Key: 0f1c9e2a-music-bed-0001" \
-H "Content-Type: application/json" \
-d '{"quote_id":"q_7Hk...","audio_url":"https://cdn.roasos.com/workspaces/ws_01/uploads/audio_url.mp3","video_url":"https://cdn.roasos.com/workspaces/ws_01/uploads/video_url.mp4"}'
# 201 { "data": { "id": "gen_...", "status": "queued", "credits_reserved": 1 } }
# 3. Poll, then read the result.
curl https://api.roasos.com/v1/jobs/gen_.../status -H "Authorization: Bearer roasos_sk_live_..."
curl https://api.roasos.com/v1/jobs/gen_.../result -H "Authorization: Bearer roasos_sk_live_..."Today
The endpoint is POST /v1/assembly/music-bed.
It is live.
See also
llms.txtfor this model — the same facts as one plain-text file for an agent.GET https://api.roasos.com/v1/catalog/music-bed— the machine-readable form: enums, defaults, limits and prices. Refer to the API reference.- Jobs — how to poll a job and read its result.
- Provider endpoints:
fal-ai/ffmpeg-api/compose.
FFmpeg Merge Videos
Merge Videos joins finished clips end to end, in the order you send them. It is the simplest way to turn a set of shots into one deliverable.
Text Overlay
Text Overlay puts one line of copy on a finished clip. The copy shows as white text in a dark, rounded card. You set the position and the time window. The clip keeps its own sound.