Skip to content

Sonilo V1.1 Video to Sound Effects

Integrate

Model id sonilo/v1.1/video-to-sound-effects
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/sonilo/v1.1/video-to-sound-effects?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Files like the example: $0.09 90 API credits · ≈ ₽9.66 your files are measured before the run Run it on this page

Get API key
Sonilo · Audio

Your first result goes here

Build a request below and run it with your API key. Outputs are copied to our storage, kept forever or 7 days for free.

Build a request

Controls are generated from the model schema. The code and the price update as you change them.

Optional sound guidance used across all scenes instead of automatic video captioning. Describe the desired audio, or leave the value empty to use automatic captions.

•required video_url
Drop a file, or

Video supplied by file upload or a public URL for sound generation, with its duration determining the generated audio's length.

Advanced audio_format · keep_speech_vocal · segments
audio_format default aac

Standalone audio format, selectable as wav, mp3, aac, or flac, with aac used by default. This selection does not change the video's audio encoding, which is always AAC.

Optional manual scene divisions, specified as time ranges with individual sound descriptions; an empty value uses automatic scene detection instead.

POST /run/sonilo/v1.1/video-to-sound-effects?wait=20 quote → $0.09
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/sonilo/v1.1/video-to-sound-effects?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Run this request

Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key

About Sonilo V1.1 Video to Sound Effects

Adds synchronized sound effects based on what happens in the video at `video_url`. An optional `prompt` steers the sound, and `segments` assigns separate descriptions to time ranges. `audio_format` can be wav, mp3, aac or flac. With `keep_speech_vocal` on, original speech is isolated and kept in the mix.

Parameters

Send either the canonical name or the native name, not both. Canonical names

NameType DefaultAllowed Description
video_urlrequired video
Typeurl · video
Video supplied by file upload or a public URL for sound generation, with its duration determining the generated audio's length.
promptoptional
Typestring | null
Optional sound guidance used across all scenes instead of automatic video captioning. Describe the desired audio, or leave the value empty to use automatic captions.
segmentsoptional
Typeobject[]
Optional manual scene divisions, specified as time ranges with individual sound descriptions; an empty value uses automatic scene detection instead.
segments[].startoptional
Typenumber
Default0
≥ 0
Segment start must be 0 for the first segment. All start times are measured in seconds relative to the beginning of the video.
segments[].endoptional
Typenumber
Default0
≥ 0
Segment ending position in seconds, bounded by the video duration for the final segment. For every earlier segment, it must coincide with the following segment's starting position so there are no gaps or overlaps.
segments[].promptoptional
Typestring
Default
Description of the segment's sound effects or foley.
audio_formatoptional
Typeenum
Defaultaac
wavmp3aacflac
Standalone audio format, selectable as wav, mp3, aac, or flac, with aac used by default. This selection does not change the video's audio encoding, which is always AAC.
keep_speech_vocaloptional
Typeboolean
Defaultfalse
Speech/vocal preservation switch affecting both audio and video outputs; disabled by default, it leaves only generated sound in the result. Enabling it uses music source separation to isolate the source vocals, discards the original music and ambience, and mixes generated sound with the unchanged vocal recording, matching its level to the voice.
required Canonical name, also accepted

File parameters take a public https:// URL, a data: URI up to 10 MB, or the file_url of an upload. Files

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "sonilo/v1.1/video-to-sound-effects",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 90,
    "usd": "0.09",
    "charged": 90,
    "refunded": 0
  },
  "input": {
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  },
  "output": {
    "audio": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_name": "0-output.mp3",
      "file_size": 1843200
    },
    "audios": [
      {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
        "content_type": "audio/mpeg",
        "file_name": "0-output.mp3",
        "file_size": 1843200
      }
    ],
    "segments": [
      {
        "index": 1,
        "start": 1.0,
        "end": 1.0,
        "meta": {
          "tags": [],
          "skipped": false,
          "skip_reason": "string"
        }
      }
    ]
  },
  "outputs": [
    {
      "type": "audio",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_size": 1843200,
      "duration": 12,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Your files, your choiceEvery outputs[].url is a copy on our storage: kept forever (paid per GB-month) or 7 days for free, by your account setting or ?storage=.
Same shape on every modeltype, url, content_type, width, height and duration, for images, video and audio alike. output is the model’s own result object.
Fields of output
audio
object {url, content_type, file_name, file_size}Generated sound encoded in the selected audio format.
audios
array of object {url, content_type, file_name, file_size}Complete collection of generated sounds, with one sound for each sample.
segments
array of object {index, start, end, meta}Segments used to generate the audio, listed in their source-video sequence.

More models: Video to Audio

For AI agents: this page as Markdown is at https://doitong.com/en-US/developers/models/sonilo/v1.1/video-to-sound-effects.md. All models and guides: https://doitong.com/developers/llms.txt