Audio

SAM Audio (Text Separation)

Credit-based pricing.

Try SAM Audio (Text Separation) →Compare models

Output

audio

Inputs

Reference audio (required)

Example prompt

drums

Try this prompt →

LLM-ready

API & LLM schema

Exact request contract for this model. Agents can fetch it from /api/v1/models?id=fal-ai/sam-audio/separate.

POST/api/v1/generate14 fields · 3 required

Field	Type	Requirement	Contract
`model_id`	constant	Required	ArtEmotion model identifier.
`extra`	object	Optional	Model-specific settings may also be nested here.
`max_credits`	number	Optional	Reject before submission if the estimated list price exceeds this cap. · Range: 1–…
`webhook_url`	string	Optional	Format: uri
`webhook_secret`	string	Optional	Optional model input.
`folder_id`	string	Optional	Optional model input.
`prompt`	string	Required	Optional model input.
`predict_spans`	boolean	Optional	Automatically predict temporal spans where the target sound occurs. · Default: false
`reranking_candidates`	number	Optional	Number of candidates to generate and rank. Higher improves quality but increases latency and cost. · Default: 1 · Range: 1–7
`acceleration`	string	Optional	Speed vs quality trade-off. Fast is quickest, Quality is most accurate. · Allowed: fast, balanced, quality · Default: balanced
`max_chunk_duration`	number	Optional	Maximum audio duration (s) to process in a single pass. Longer audio is chunked with overlap and blended. · Default: 60 · Range: 10–60
`chunk_overlap`	number	Optional	Overlap duration (s) between chunks for crossfade blending. · Default: 5 · Range: 0–30
`output_format`	string	Optional	Output audio format. · Allowed: wav, mp3 · Default: wav
`audio_url`	string	Required	Format: uri

Minimal request example

{
  "model_id": "fal-ai/sam-audio/separate",
  "prompt": "drums",
  "audio_url": "https://example.com/audio"
}

Raw JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://www.artemotion.ai/api/v1/models?id=fal-ai%2Fsam-audio%2Fseparate",
  "title": "SAM Audio (Text Separation) generation request",
  "description": "Request body accepted by POST /api/v1/generate for fal-ai/sam-audio/separate.",
  "type": "object",
  "properties": {
    "model_id": {
      "type": "string",
      "const": "fal-ai/sam-audio/separate",
      "description": "ArtEmotion model identifier."
    },
    "extra": {
      "type": "object",
      "additionalProperties": true,
      "description": "Model-specific settings may also be nested here."
    },
    "max_credits": {
      "type": "number",
      "minimum": 1,
      "description": "Reject before submission if the estimated list price exceeds this cap."
    },
    "webhook_url": {
      "type": "string",
      "format": "uri",
      "maxLength": 2048
    },
    "webhook_secret": {
      "type": "string",
      "maxLength": 512
    },
    "folder_id": {
      "type": "string"
    },
    "prompt": {
      "type": "string"
    },
    "predict_spans": {
      "title": "Predict Spans",
      "description": "Automatically predict temporal spans where the target sound occurs.",
      "default": false,
      "type": "boolean"
    },
    "reranking_candidates": {
      "title": "Reranking Candidates",
      "description": "Number of candidates to generate and rank. Higher improves quality but increases latency and cost.",
      "default": 1,
      "type": "number",
      "minimum": 1,
      "maximum": 7,
      "multipleOf": 1
    },
    "acceleration": {
      "title": "Acceleration",
      "description": "Speed vs quality trade-off. Fast is quickest, Quality is most accurate.",
      "default": "balanced",
      "type": "string",
      "enum": [
        "fast",
        "balanced",
        "quality"
      ]
    },
    "max_chunk_duration": {
      "title": "Max Chunk Duration (s)",
      "description": "Maximum audio duration (s) to process in a single pass. Longer audio is chunked with overlap and blended.",
      "default": 60,
      "type": "number",
      "minimum": 10,
      "maximum": 60,
      "multipleOf": 1
    },
    "chunk_overlap": {
      "title": "Chunk Overlap (s)",
      "description": "Overlap duration (s) between chunks for crossfade blending.",
      "default": 5,
      "type": "number",
      "minimum": 0,
      "maximum": 30,
      "multipleOf": 1
    },
    "output_format": {
      "title": "Output Format",
      "description": "Output audio format.",
      "default": "wav",
      "type": "string",
      "enum": [
        "wav",
        "mp3"
      ]
    },
    "audio_url": {
      "type": "string",
      "format": "uri"
    }
  },
  "required": [
    "model_id",
    "prompt",
    "audio_url"
  ],
  "additionalProperties": false
}

Browse schemas for every ArtEmotion model →

FAQ

How much does SAM Audio (Text Separation) cost on ArtEmotion?

Credit-based pricing. You pay in ArtEmotion credits — every plan and top-up converts USD to credits at a fixed rate.

Do I get my credits back if SAM Audio (Text Separation) fails?

Yes — failed generations are never charged. The credits are released back to your balance automatically.

Can I call SAM Audio (Text Separation) from the API?

Yes. Use POST /api/v1/generate with model_id: "fal-ai/sam-audio/separate". See the API reference for the full schema.

Where are my generations stored?

Every output is saved to your personal Library. You can export or delete everything any time from Privacy & deletion.

Ready to generate with SAM Audio (Text Separation)?

Start now →

No commitment. New accounts get 50 free credits on signup. See pricing.