Générer une vidéo

curl --request POST \
  --url https://api.samsa.ai/public/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "mode": "image_to_video",
  "image": {
    "url": "https://cdn.example.com/start-frame.png"
  },
  "end_image": {
    "url": "https://cdn.example.com/end-frame.png"
  },
  "prompt": "The camera slowly pans right as waves roll in",
  "engine": "veo_3_1_lite",
  "duration": 8,
  "aspect_ratio": "16:9",
  "resolution": "720p"
}
'

{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "mode": "<string>",
  "estimated_credits": 123
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "aspect_ratio"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "aspect_ratio"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "aspect_ratio"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "aspect_ratio"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "aspect_ratio"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "aspect_ratio"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "aspect_ratio"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "aspect_ratio"
  }
}

POST

videos

generations

curl --request POST \
  --url https://api.samsa.ai/public/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "mode": "image_to_video",
  "image": {
    "url": "https://cdn.example.com/start-frame.png"
  },
  "end_image": {
    "url": "https://cdn.example.com/end-frame.png"
  },
  "prompt": "The camera slowly pans right as waves roll in",
  "engine": "veo_3_1_lite",
  "duration": 8,
  "aspect_ratio": "16:9",
  "resolution": "720p"
}
'

{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "mode": "<string>",
  "estimated_credits": 123
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "aspect_ratio"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "aspect_ratio"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "aspect_ratio"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "aspect_ratio"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "aspect_ratio"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "aspect_ratio"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "aspect_ratio"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "aspect_ratio"
  }
}

Soumets un job de génération de vidéo. Le champ mode sélectionne la forme de la requête (image_to_video, text_to_video ou text_to_video_styled) et l’appel renvoie 202 Accepted avec un id de job ; interroge GET /videos/generations/{id} pour le résultat. Consulte GET /videos/models pour connaître la prise en charge de duration, resolution, aspect_ratio, frame de fin et audio de chaque engine.

Exemple : image-to-video avec une frame de départ et de fin

En mode image_to_video, image est la frame de départ et end_image une frame de fin optionnelle (uniquement sur les engines qui prennent en charge la frame de fin — voir supports_end_frame dans GET /videos/models). Chaque frame prend exactement un parmi image_id, url, ou base64 + mime_type.

curl -X POST https://api.samsa.ai/public/v1/videos/generations \
  -H "Authorization: Bearer $SAMSA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "mode": "image_to_video",
    "image": { "url": "https://cdn.example.com/start-frame.png" },
    "end_image": { "url": "https://cdn.example.com/end-frame.png" },
    "prompt": "The camera slowly pans right as waves roll in",
    "engine": "veo_3_1_lite",
    "duration": 8,
    "aspect_ratio": "16:9",
    "resolution": "720p"
  }'

{
  "mode": "image_to_video",
  "image": { "url": "https://cdn.example.com/start-frame.png" },
  "end_image": { "url": "https://cdn.example.com/end-frame.png" },
  "prompt": "The camera slowly pans right as waves roll in",
  "engine": "veo_3_1_lite",
  "duration": 8,
  "aspect_ratio": "16:9",
  "resolution": "720p"
}

duration est requis et doit être une valeur prise en charge par l’engine (voir durations dans GET /videos/models) — une valeur non prise en charge renvoie 422. Pour text_to_video_styled, style_id est requis aux côtés de prompt et duration ; le menu déroulant du corps de requête ci-dessus montre les trois modes.

Autorisations

Authorization

string

header

requis

Organization API key as a bearer token: Authorization: Bearer samsa_sk_....

Corps

application/json

PublicImageToVideoRequest
PublicTextToVideoRequest
PublicTextToVideoStyledRequest

mode: image_to_video — animate a start frame (optional end frame).

duration

integer

requis

Clip length in seconds. Each engine supports a specific set — see durations in GET /videos/models. Unsupported values return 422.

Exemple:

8

image

PublicVideoFrame · object

requis

The start frame: exactly one of image_id, url, or base64+mime_type.

Show child attributes

engine

string | null

Video engine — a public engine id from GET /videos/models (e.g. veo_3_1_lite, the default). Unknown engines return 422.

Exemple:

"veo_3_1_lite"

aspect_ratio

string

défaut:16:9

Aspect ratio — 16:9, 9:16, or 1:1 (engine-dependent; see aspect_ratios in GET /videos/models).

Exemple:

"16:9"

resolution

string | null

Output resolution — 720p, 1080p, or 4k where the engine supports it (see resolutions in GET /videos/models). Omit to use the engine default. Credits scale with the engine's resolution multipliers.

Exemple:

"720p"

generate_audio

boolean

défaut:false

Generate audio with the video — audio-capable engines only (see supports_audio in GET /videos/models); adds the engine's audio credit multiplier.

Exemple:

false

webhook_url

string | null

Optional https webhook notified once on terminal status (signed per the webhook signature scheme; see the webhooks docs).

Exemple:

"https://example.com/webhooks/samsa"

mode

string

défaut:image_to_video

Allowed value: "image_to_video"

end_image

PublicVideoFrame · object | null

Optional end frame — only for end-frame-capable engines (see supports_end_frame in GET /videos/models).

Show child attributes

prompt

string | null

Optional text prompt guiding the motion.

Minimum string length: 1

Exemple:

"The camera slowly pans right as waves roll in"

Réponse

Successful Response

202 body for POST /videos/generations (ADR §7.1).

string<uuid>

requis

The video job id — poll GET /videos/generations/{id}.

status

enum<string>

requis

Initial status: always pending at submit.

Options disponibles:

pending,

processing,

completed,

failed,

cancelled

Exemple:

"pending"

mode

string

requis

The requested mode — image_to_video, text_to_video, or text_to_video_styled.

Exemple:

"text_to_video"

estimated_credits

integer

requis

Credits this job is expected to cost (base 5/sec x engine multiplier x resolution x audio; styled adds a flat 10 for the intermediate image).

Exemple:

80

Aperçu Récupérer une génération de vidéo

Prise en main

APIs

Vérification de contenu

Générer une vidéo

Exemple : image-to-video avec une frame de départ et de fin

Autorisations

Corps

Réponse

​Exemple : image-to-video avec une frame de départ et de fin

Autorisations

Corps

Réponse

Exemple : image-to-video avec une frame de départ et de fin