Runway
App · 25 actions
Generate video, images and audio, inspect or cancel tasks, manage knowledge documents and read avatars, voices and usage.
Actions
| Action | What it does |
|---|---|
| Cancel or delete a task | Cancel or delete a task. |
| Create document | Create document. |
| Delete document | Delete document. |
| Get a voice | Get a voice. |
| Get avatar | Get avatar. |
| Get conversation | Get conversation. |
| Get document | Get document. |
| Get organization information | Get organization information. |
| Get task detail | Get task detail. |
| Image to video | Image to video. |
| Image upscale | Image upscale. |
| List avatars | List avatars. |
| List conversations | List conversations. |
| List documents | List documents. |
| List voices | List voices. |
| Query credit usage | Query credit usage. |
| Sound effect | Sound effect. |
| Text to image | Text to image. |
| Text to speech | Text to speech. |
| Text to video | Text to video. |
| Update document | Update document. |
| Video to video | Video to video. |
| Video upscale | Video upscale. |
| Voice dubbing | Voice dubbing. |
| Voice isolation | Voice isolation. |
Cancel or delete a task
Cancel or delete a task.
Inputs
- ID
idtextRequired - The ID of a previously-submitted task that has not been canceled or deleted.
Outputs
datanull- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": null,
"has_more": false,
"next_cursor": "example"
}Create document
Create document.
Inputs
- Name
nametextRequired - A descriptive name for the document.
- Content
contenttextRequired - The markdown or plain text content of the document.
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"content": "example",
"createdAt": "2026-01-01T00:00:00Z",
"id": "11111111-1111-4111-8111-111111111111",
"name": "example",
"type": "text",
"updatedAt": "2026-01-01T00:00:00Z",
"usedBy": []
},
"has_more": false,
"next_cursor": "example"
}Delete document
Delete document.
Inputs
- ID
idtextRequired - The document ID.
Outputs
datanull- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": null,
"has_more": false,
"next_cursor": "example"
}Get a voice
Get a voice.
Inputs
- ID
idtextRequired - The ID of the voice to retrieve.
Outputs
dataobject- A voice that is still being processed.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"createdAt": "2026-01-01T00:00:00Z",
"description": null,
"id": "11111111-1111-4111-8111-111111111111",
"name": "example",
"status": "PROCESSING"
},
"has_more": false,
"next_cursor": "example"
}Get avatar
Get avatar.
Inputs
- ID
idtextRequired - Id
Outputs
dataobject- An avatar that is still being processed.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"createdAt": "2026-01-01T00:00:00Z",
"documentIds": [],
"id": "11111111-1111-4111-8111-111111111111",
"name": "example",
"personality": "example",
"processedImageUri": null,
"referenceImageUri": null,
"startScript": null,
"status": "PROCESSING",
"updatedAt": "2026-01-01T00:00:00Z",
"voice": {
"description": "example",
"name": "example",
"presetId": "victoria",
"type": "runway-live-preset"
}
},
"has_more": false,
"next_cursor": "example"
}Get conversation
Get conversation.
Inputs
- ID
idtextRequired - The conversation ID. This is the same value as the realtime session ID for the call.
Outputs
dataobject- A conversation that is currently active.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"avatar": null,
"createdAt": "2026-01-01T00:00:00Z",
"duration": null,
"id": "11111111-1111-4111-8111-111111111111",
"maxDuration": null,
"name": "example",
"recordingUrl": null,
"startedAt": null,
"status": "in_progress",
"tools": [],
"transcript": []
},
"has_more": false,
"next_cursor": "example"
}Get document
Get document.
Inputs
- ID
idtextRequired - The document ID.
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"content": "example",
"createdAt": "2026-01-01T00:00:00Z",
"id": "11111111-1111-4111-8111-111111111111",
"name": "example",
"type": "text",
"updatedAt": "2026-01-01T00:00:00Z",
"usedBy": []
},
"has_more": false,
"next_cursor": "example"
}Get organization information
Get organization information.
Inputs
None.
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"creditBalance": 0,
"tier": {
"maxMonthlyCreditSpend": 0,
"models": {}
},
"usage": {
"models": {}
}
},
"has_more": false,
"next_cursor": "example"
}Get task detail
Get task detail.
Inputs
- ID
idtextRequired - The ID of a previously-submitted task that has not been canceled or deleted.
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"cost": {
"credits": -9007199254740991
},
"createdAt": "2026-01-01T00:00:00Z",
"estimatedCost": {
"credits": 0
},
"failure": "example",
"failureCode": "example",
"id": "11111111-1111-4111-8111-111111111111",
"output": [],
"progress": 0,
"status": "SUCCEEDED"
},
"has_more": false,
"next_cursor": "example"
}Image to video
Image to video.
Inputs
- PromptText
promptTexttextRequired - A non-empty string up to 1000 characters (measured in UTF-16 code units). This should describe in detail what should appear in the output.
- PromptImage
promptImagetextRequired - A HTTPS URL, Runway upload URI, or base64 data URI (e.g. `data:image/png;base64,...`, up to 5MB) containing an encoded image. See [our docs](/assets/inputs#images) on image inputs for more information.
- Seed
seednumber - If unspecified, a random number is chosen. Varying the seed integer is a way to get different results for the same other request parameters. Using the same seed integer for an identical request will produce similar results.From 0 to 4294967295.
- Ratio
ratiotextRequired - The resolution of the output video.One of:
1280:720,720:1280,1104:832,960:960,832:1104,1584:672. - Duration
durationnumberRequired - The number of seconds of duration for the output video. Must be an integer from 2 to 10.From 2 to 10.
- ContentModeration
contentModerationobject - Settings that affect the behavior of the content moderation system.
- OutputFormat
outputFormattext - The container/encoding of the output. `mp4` (default) returns an H.264 .mp4. `prores` returns a ProRes .mov. `png_sequence` returns a .zip of PNG frames (plus a separate .wav artifact when the output has audio). `hdr10` (HEVC Main 10, BT.2020 + PQ) and `hlg` (HEVC Main 10, BT.2020 + HLG) return true-HDR 10-bit .mp4s; `sdr_rec709_10bit` returns a 10-bit Rec.709 HEVC .mp4 for SDR grading pipelines; `hdr_pq_12bit_master` returns a 12-bit 4:4:4 BT.2020 + PQ HEVC .mov with measured HDR10 content-light metadata for mastering; `hdr_prores` returns a BT.2020 + PQ ProRes .mov editorial mezzanine, whose tier is selectable with `proresProfile` (`422`, `422 HQ`, or `4444`; defaults to `422 HQ`); `hdr_png_sequence` returns a .zip of 16-bit PNG frames carrying the PQ signal losslessly (plus a colorimetry.json sidecar and a separate .wav when the output has audio); `hdr_exr_sequence` returns a .zip of half-float OpenEXR frames carrying the HDR signal as linear BT.2020 display light, 1.0 = 100 nits (plus a colorimetry.json sidecar and a separate .wav when the output has audio); `hdr_exr_acescg_sequence_1_3` returns the same delivery as scene-referred ACEScg (inverted through the ACES 1.3 Output Transform), reading correctly with the stock `ACES - ACEScg` input transform in ACES-configured pipelines, with VFX sequence frame naming (frame.0001.exr). Non-mp4 formats incur an additional per-second credit surcharge: 5 credits per second for `prores` and `png_sequence`, and 20 credits per second for every 10-bit and deeper profile (including the 12-bit, 16-bit, and EXR ones), rising to 40 credits per second when the output is larger than 4 megapixels : that includes 1440p (2560x1440 is under the line, but anything larger crosses it) up through 4K.One of:
mp4,prores,png_sequence,hdr10,hlg,sdr_rec709_10bit,hdr_pq_12bit_master,hdr_prores,hdr_png_sequence,hdr_exr_sequence,hdr_exr_acescg_sequence_1_3,hdr_exr_acescg_sequence_2_0. - ProresProfile
proresProfiletext - The ProRes profile to use. Only valid when `outputFormat` is `prores` or `hdr_prores`. For `prores`, any profile is accepted and the default is `4444`. For `hdr_prores`, only `422`, `422 HQ` and `4444` are available and the default is `422 HQ` : `422 Proxy` and `422 LT` quantize too heavily to hold the HDR gradients, and 12-bit output is served by `hdr_pq_12bit_master` instead of `4444 XQ`.One of:
422,4444,422 Proxy,422 LT,422 HQ,4444 XQ. - Model
modeltextRequired - ModelOne of:
gen4.5.
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"estimatedCost": {
"credits": 0
},
"id": "11111111-1111-4111-8111-111111111111"
},
"has_more": false,
"next_cursor": "example"
}Image upscale
Image upscale.
Inputs
- ImageUri
imageUritextRequired - A HTTPS URL, Runway upload URI, or base64 data URI (e.g. `data:image/png;base64,...`, up to 5MB) containing an encoded image. See [our docs](/assets/inputs#images) on image inputs for more information.
- ScaleFactor
scaleFactornumber - Multiplies each input dimension to produce output width and height. Defaults to 2.One of:
2,4,8,16. - Sharpen
sharpennumber - Sharpness intensity from 0 (none) to 100.From 0 to 100.
- SmartGrain
smartGrainnumber - Grain and texture enhancement from 0 to 100.From 0 to 100.
- UltraDetail
ultraDetailnumber - Fine detail enhancement from 0 to 100.From 0 to 100.
- Flavor
flavortext - Optimization preset: `sublime` (illustration), `photo` (photographic), or `photo_denoiser` (noisy photos).One of:
sublime,photo,photo_denoiser. - Model
modeltextRequired - ModelOne of:
magnific_precision_upscaler_v2.
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"estimatedCost": {
"credits": 0
},
"id": "11111111-1111-4111-8111-111111111111"
},
"has_more": false,
"next_cursor": "example"
}List avatars
List avatars.
Inputs
- Cursor
cursortext - Cursor from a previous response for fetching the next page of results.
- Limit
limitnumber - The maximum number of items to return per page.From 1 to 100.
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"data": [],
"hasMore": false,
"nextCursor": null
},
"has_more": false,
"next_cursor": "example"
}List conversations
List conversations.
Inputs
- Cursor
cursortext - Cursor from a previous response for fetching the next page of results.
- Limit
limitnumber - The maximum number of items to return per page.From 1 to 100.
- Avatar
avatartext - Filter to conversations that used the given custom avatar.
- StartDate
startDatedate and time - Filter conversations created on or after this timestamp (inclusive).
- EndDate
endDatedate and time - Filter conversations created before this timestamp (exclusive).
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"data": [],
"hasMore": false,
"nextCursor": null
},
"has_more": false,
"next_cursor": "example"
}List documents
List documents.
Inputs
- Cursor
cursortext - Cursor from a previous response for fetching the next page of results.
- Limit
limitnumber - The maximum number of items to return per page.From 1 to 100.
- Sort
sorttext - Field to sort results by.One of:
createdAt,updatedAt. - Order
ordertext - Sort direction.One of:
asc,desc.
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"data": [],
"hasMore": false,
"nextCursor": null
},
"has_more": false,
"next_cursor": "example"
}List voices
List voices.
Inputs
- Cursor
cursortext - Cursor from a previous response for fetching the next page of results.
- Limit
limitnumber - The maximum number of items to return per page.From 1 to 100.
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"data": [],
"hasMore": false,
"nextCursor": null
},
"has_more": false,
"next_cursor": "example"
}Query credit usage
Query credit usage.
Inputs
- StartDate
startDatedate - The start date of the usage data in ISO-8601 format (YYYY-MM-DD). If unspecified, it will default to 30 days before the current date. All dates are in UTC.
- BeforeDate
beforeDatedate - The end date of the usage data in ISO-8601 format (YYYY-MM-DD), not inclusive. If unspecified, it will default to thirty days after the start date. Must be less than or equal to 90 days after the start date. All dates are in UTC.
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"apiKeys": [],
"models": [],
"results": [],
"resultsByApiKey": []
},
"has_more": false,
"next_cursor": "example"
}Sound effect
Sound effect.
Inputs
- PromptText
promptTexttextRequired - A non-empty text prompt. For text-to-speech, the words to speak. For text-to-audio, a scene description that can include voice direction, dialogue, music, and sound effects.
- ReferenceAudios
referenceAudioslist - Up to three reference audio clips. When provided, reference them in promptText as @Audio1, @Audio2, and @Audio3 in order.
- SpeechRate
speechRatenumber - Relative speech speed. Negative is slower, positive is faster; 0 is normal.From -50 to 100.
- LoudnessRate
loudnessRatenumber - Relative output loudness. Negative is quieter, positive is louder; 0 is normal.From -50 to 100.
- PitchRate
pitchRatenumber - Pitch shift in semitones. Negative lowers, positive raises; 0 is unchanged.From -12 to 12.
- SampleRate
sampleRatenumber - Output sample rate in Hz.One of:
8000,16000,24000,32000,44100,48000. - OutputFormat
outputFormattext - Output audio container/format.One of:
wav,mp3,ogg_opus. - Model
modeltextRequired - ModelOne of:
seed_audio.
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"estimatedCost": {
"credits": 0
},
"id": "11111111-1111-4111-8111-111111111111"
},
"has_more": false,
"next_cursor": "example"
}Text to image
Text to image.
Inputs
- PromptText
promptTexttextRequired - A non-empty string up to 1000 characters (measured in UTF-16 code units). This should describe in detail what should appear in the output.
- Seed
seednumber - If unspecified, a random number is chosen. Varying the seed integer is a way to get different results for the same other request parameters. Using the same seed integer for an identical request will produce similar results.From 0 to 4294967295.
- Ratio
ratiotextRequired - The resolution of the output image.One of:
1024:1024,1080:1080,1168:880,1360:768,1440:1080,1080:1440,1808:768,1920:1080,1080:1920,2112:912, and 6 more. - ReferenceImages
referenceImageslistRequired - An array of one to three images to be used as references for the generated image output.
- ContentModeration
contentModerationobject - Settings that affect the behavior of the content moderation system.
- Model
modeltextRequired - ModelOne of:
gen4_image_turbo.
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"estimatedCost": {
"credits": 0
},
"id": "11111111-1111-4111-8111-111111111111"
},
"has_more": false,
"next_cursor": "example"
}Text to speech
Text to speech.
Inputs
- PromptText
promptTexttextRequired - A non-empty text prompt. For text-to-speech, the words to speak. For text-to-audio, a scene description that can include voice direction, dialogue, music, and sound effects.
- Voice
voiceobject - The voice to use for text-to-speech generation. If omitted, a default voice is used.
- SpeechRate
speechRatenumber - Relative speech speed. Negative is slower, positive is faster; 0 is normal.From -50 to 100.
- LoudnessRate
loudnessRatenumber - Relative output loudness. Negative is quieter, positive is louder; 0 is normal.From -50 to 100.
- PitchRate
pitchRatenumber - Pitch shift in semitones. Negative lowers, positive raises; 0 is unchanged.From -12 to 12.
- SampleRate
sampleRatenumber - Output sample rate in Hz.One of:
8000,16000,24000,32000,44100,48000. - OutputFormat
outputFormattext - Output audio container/format.One of:
wav,mp3,ogg_opus. - Model
modeltextRequired - ModelOne of:
seed_audio.
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"estimatedCost": {
"credits": 0
},
"id": "11111111-1111-4111-8111-111111111111"
},
"has_more": false,
"next_cursor": "example"
}Text to video
Text to video.
Inputs
- PromptText
promptTexttextRequired - A non-empty string up to 1000 characters (measured in UTF-16 code units). This should describe in detail what should appear in the output.
- Ratio
ratiotextRequired - The resolution of the output video.One of:
1280:720,720:1280. - Duration
durationnumberRequired - The number of seconds of duration for the output video. Must be an integer from 2 to 10.From 2 to 10.
- Seed
seednumber - If unspecified, a random number is chosen. Varying the seed integer is a way to get different results for the same other request parameters. Using the same seed integer for an identical request will produce similar results.From 0 to 4294967295.
- ContentModeration
contentModerationobject - Settings that affect the behavior of the content moderation system.
- OutputFormat
outputFormattext - The container/encoding of the output. `mp4` (default) returns an H.264 .mp4. `prores` returns a ProRes .mov. `png_sequence` returns a .zip of PNG frames (plus a separate .wav artifact when the output has audio). `hdr10` (HEVC Main 10, BT.2020 + PQ) and `hlg` (HEVC Main 10, BT.2020 + HLG) return true-HDR 10-bit .mp4s; `sdr_rec709_10bit` returns a 10-bit Rec.709 HEVC .mp4 for SDR grading pipelines; `hdr_pq_12bit_master` returns a 12-bit 4:4:4 BT.2020 + PQ HEVC .mov with measured HDR10 content-light metadata for mastering; `hdr_prores` returns a BT.2020 + PQ ProRes .mov editorial mezzanine, whose tier is selectable with `proresProfile` (`422`, `422 HQ`, or `4444`; defaults to `422 HQ`); `hdr_png_sequence` returns a .zip of 16-bit PNG frames carrying the PQ signal losslessly (plus a colorimetry.json sidecar and a separate .wav when the output has audio); `hdr_exr_sequence` returns a .zip of half-float OpenEXR frames carrying the HDR signal as linear BT.2020 display light, 1.0 = 100 nits (plus a colorimetry.json sidecar and a separate .wav when the output has audio); `hdr_exr_acescg_sequence_1_3` returns the same delivery as scene-referred ACEScg (inverted through the ACES 1.3 Output Transform), reading correctly with the stock `ACES - ACEScg` input transform in ACES-configured pipelines, with VFX sequence frame naming (frame.0001.exr). Non-mp4 formats incur an additional per-second credit surcharge: 5 credits per second for `prores` and `png_sequence`, and 20 credits per second for every 10-bit and deeper profile (including the 12-bit, 16-bit, and EXR ones), rising to 40 credits per second when the output is larger than 4 megapixels : that includes 1440p (2560x1440 is under the line, but anything larger crosses it) up through 4K.One of:
mp4,prores,png_sequence,hdr10,hlg,sdr_rec709_10bit,hdr_pq_12bit_master,hdr_prores,hdr_png_sequence,hdr_exr_sequence,hdr_exr_acescg_sequence_1_3,hdr_exr_acescg_sequence_2_0. - ProresProfile
proresProfiletext - The ProRes profile to use. Only valid when `outputFormat` is `prores` or `hdr_prores`. For `prores`, any profile is accepted and the default is `4444`. For `hdr_prores`, only `422`, `422 HQ` and `4444` are available and the default is `422 HQ` : `422 Proxy` and `422 LT` quantize too heavily to hold the HDR gradients, and 12-bit output is served by `hdr_pq_12bit_master` instead of `4444 XQ`.One of:
422,4444,422 Proxy,422 LT,422 HQ,4444 XQ. - Model
modeltextRequired - ModelOne of:
gen4.5.
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"estimatedCost": {
"credits": 0
},
"id": "11111111-1111-4111-8111-111111111111"
},
"has_more": false,
"next_cursor": "example"
}Update document
Update document.
Inputs
- ID
idtextRequired - The document ID.
- Name
nametext - A new name for the document.
- Content
contenttext - New markdown or plain text content for the document.
Outputs
datanull- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": null,
"has_more": false,
"next_cursor": "example"
}Video to video
Video to video.
Inputs
- PromptText
promptTexttext - A non-empty and optional string describing what should appear in the output.
- Keyframes
keyframeslist - Timed guidance images placed at specific points in the input video. Up to 5 keyframes.
- VideoUri
videoUritextRequired - A HTTPS URL, Runway upload URI, or base64 data URI (e.g. `data:video/mp4;base64,...`, up to 5MB) containing an encoded video. See [our docs](/assets/inputs#videos) on video inputs for more information.
- Seed
seednumber - If unspecified, a random number is chosen. Varying the seed integer is a way to get different results for the same other request parameters. Using the same seed integer for an identical request will produce similar results.From 0 to 4294967295.
- Ratio
ratiotext - Ratio
- TargetAspectRatio
targetAspectRatiotext - Target aspect ratio for expand/outpaint. Letterboxes the input video and keyframes before generation.One of:
16:9,4:3,3:2,1:1,2:3,3:4,9:16,21:9. - ContentModeration
contentModerationobject - Settings that affect the behavior of the content moderation system.
- OutputFormat
outputFormattext - The container/encoding of the output. `mp4` (default) returns an H.264 .mp4. `prores` returns a ProRes .mov. `png_sequence` returns a .zip of PNG frames. `sdr_rec709_10bit` returns a 10-bit Rec.709 HEVC .mp4 for SDR grading pipelines. Non-mp4 formats incur an additional surcharge: 5 credits per second for `prores` and `png_sequence`, and 20 credits per second for `sdr_rec709_10bit` : 40 credits per second when the output is larger than 4 megapixels : includes anything larger than 1440p, up through 4K.One of:
mp4,prores,png_sequence,sdr_rec709_10bit. - ProresProfile
proresProfiletext - The ProRes profile to use. Only valid when `outputFormat` is `prores`. Defaults to `4444`. Note: generated content contains no transparency : the alpha channel in `4444` / `4444 XQ` outputs is present but fully opaque; choose these tiers for 12-bit 4:4:4 color fidelity, not for mattes.One of:
422,4444,422 Proxy,422 LT,422 HQ,4444 XQ. - Model
modeltextRequired - ModelOne of:
aleph2.
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"estimatedCost": {
"credits": 0
},
"id": "11111111-1111-4111-8111-111111111111"
},
"has_more": false,
"next_cursor": "example"
}Video upscale
Video upscale.
Inputs
- VideoUri
videoUritextRequired - A HTTPS URL, Runway upload URI, or base64 data URI (e.g. `data:video/mp4;base64,...`, up to 5MB) containing an encoded video. See [our docs](/assets/inputs#videos) on video inputs for more information.
- Resolution
resolutiontext - Target output resolution from 720p to 4k. Defaults to `2k`.One of:
720p,1k,2k,4k. - Creativity
creativitynumber - How much AI-generated detail to add during upscaling, from 0 (faithful) to 100.From 0 to 100.
- Sharpen
sharpennumber - Sharpness intensity from 0 (none) to 100.From 0 to 100.
- SmartGrain
smartGrainnumber - Grain and texture enhancement from 0 to 100.From 0 to 100.
- Flavor
flavortext - Processing style: `vivid` for enhanced color and detail, `natural` for faithful reproduction.One of:
vivid,natural. - FpsBoost
fpsBoosttrue/false - Whether to increase the output frame rate.
- Model
modeltextRequired - ModelOne of:
magnific_video_upscaler_creative.
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"estimatedCost": {
"credits": 0
},
"id": "11111111-1111-4111-8111-111111111111"
},
"has_more": false,
"next_cursor": "example"
}Voice dubbing
Voice dubbing.
Inputs
- AudioUri
audioUritextRequired - A HTTPS URL, Runway upload URI, or base64 data URI (e.g. `data:audio/mp3;base64,...`, up to 5MB) containing an encoded audio. See [our docs](/assets/inputs#audio) on audio inputs for more information.
- TargetLang
targetLangtextRequired - The target language code to dub the audio to (e.g., "es" for Spanish, "fr" for French).One of:
en,hi,pt,zh,es,fr,de,ja,ar,ru, and 19 more. - DisableVoiceCloning
disableVoiceCloningtrue/false - Whether to disable voice cloning and use a generic voice instead.
- DropBackgroundAudio
dropBackgroundAudiotrue/false - Whether to remove background audio from the dubbed output.
- NumSpeakers
numSpeakersnumber - The number of speakers in the audio. If not provided, it will be detected automatically.At most 9007199254740991.
- Model
modeltextRequired - ModelOne of:
eleven_voice_dubbing.
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"estimatedCost": {
"credits": 0
},
"id": "11111111-1111-4111-8111-111111111111"
},
"has_more": false,
"next_cursor": "example"
}Voice isolation
Voice isolation.
Inputs
- AudioUri
audioUritextRequired - A HTTPS URL, Runway upload URI, or base64 data URI (e.g. `data:audio/mp3;base64,...`, up to 5MB) containing an encoded audio. See [our docs](/assets/inputs#audio) on audio inputs for more information.
- Model
modeltextRequired - ModelOne of:
eleven_voice_isolation.
Outputs
dataobject- The response returned by the service.
has_moretrue/false- Whether another page is available.
next_cursortext- Continuation token for the next page.
Example output
{
"data": {
"estimatedCost": {
"credits": 0
},
"id": "11111111-1111-4111-8111-111111111111"
},
"has_more": false,
"next_cursor": "example"
}