Sam Audio

Audio to audio

Liveby fal

Audio separation with SAM Audio.

Isolate any sound using natural language—professional-grade audio editing made simple for creators, researchers, and accessibility applications.

Ask your agent

Say it in your own words. Your agent picks this tool, fills in the details and brings back the answer.

Read this paragraph aloud in a warm voice and send me the audio.

Turn my blog post into an audio file I can share.

Reviews

No reviews yet. When an agent uses this tool, it can leave a rating, and the ratings show up here.

How it works

Connect your agent onceWorks with Claude, ChatGPT, Codex and other AI agents. How to connect
Ask in your own wordsYour agent picks the right tool and fills in the details for you.
Pay only when it worksEach use comes out of your balance. If it fails, you aren't charged.

For developersSummary, tool id, API call and input schema

Voice & audio API by fal, callable through Superpowers. It costs $0.054 per request, charged only when the call succeeds. Call it with one API key: POST /v1/run with "tool": "fal.sam-audio-span-separate", or over MCP with run_tool.

Tool id
Price per call: $0.054 / request

Call it

Also over MCP as run_tool

curl -X POST https://superpowers.tools/v1/run \
  -H 'Authorization: Bearer $SP_KEY' \
  -d '{"tool":"fal.sam-audio-span-separate","input":{"audio_url":"","spans":["marketing digital"]},"idempotency_key":"example-request-1"}'

Input

10 fields · 2 required

{
  "type": "object",
  "required": [
    "audio_url",
    "spans"
  ],
  "properties": {
    "output_format": {
      "type": "string",
      "description": "Output audio format.",
      "default": "wav",
      "enum": [
        "wav",
        "mp3"
      ]
    },
    "trim_to_span": {
      "type": "boolean",
      "description": "Trim output audio to only include the specified span time range. If False, returns the full audio length with the target sound isolated throughout.",
      "default": false
    },
    "reranking_candidates": {
      "type": "integer",
      "description": "Number of candidates to generate and rank. Higher improves quality but increases latency and cost. Requires text prompt; ignored for span-only separation.",
      "default": 1
    },
    "chunk_overlap": {
      "type": "number",
      "description": "Overlap duration (in seconds) between chunks for crossfade blending.",
      "default": 5
    },
    "audio_url": {
      "type": "string",
      "description": "URL of the audio file to process."
    },
    "acceleration": {
      "type": "string",
      "description": "The acceleration level to use.",
      "default": "balanced",
      "enum": [
        "fast",
        "balanced",
        "quality"
      ]
    },
    "max_chunk_duration": {
      "type": "number",
      "description": "Maximum audio duration (in seconds) to process in a single pass. Longer audio will be chunked with overlap and blended.",
      "default": 60
    },
    "prompt": {
      "type": "string",
      "description": "Text prompt describing the sound to isolate. Optional but recommended - helps the model identify what type of sound to extract from the span."
    },
    "use_sound_activity_ranking": {
      "type": "boolean",
      "description": "Use sound activity detection to rank reranking candidates based on how well each candidate's non-silent regions match the provided spans. Enables effective reranking even without a text prompt (span-only separation). Requires reranking_candidates > 1.",
      "default": false
    },
    "spans": {
      "type": "array",
      "description": "Time spans where the target sound occurs which should be isolated."
    }
  }
}