{
  "data": {
    "id": "SogOChnbEL31XZWeO",
    "userId": "e5eBfwJfZr4LIY9GC",
    "name": "audio-transcriber",
    "username": "pennydata",
    "description": "Audio transcriber and speech to text: transcribe mp3, wav, m4a, mp4, webm, mov URLs or podcast RSS with Whisper, timestamps, SRT and VTT. No API key. $6 per 1,000 audio minutes, first 2 minutes of each run free, failed files free.",
    "isPublic": true,
    "createdAt": "2026-10-21T14:35:57.162Z",
    "modifiedAt": "2026-10-24T04:02:58.719Z",
    "taggedBuilds": {
      "latest": {
        "buildId": "LPvbOvNPTp7gPZw5Q",
        "finishedAt": "2026-10-24T02:09:54.593Z",
        "buildNumberInt": 100011,
        "buildNumber": "0.1.11"
      }
    },
    "stats": {
      "totalBuilds": 11,
      "totalRuns": 3,
      "totalUsers": 2,
      "totalUsers7Days": 1,
      "totalUsers30Days": 1,
      "totalUsers90Days": 1,
      "lastRunStartedAt": "2026-10-24T01:30:31.709Z",
      "actorReviewCount": 0,
      "actorReviewRating": 0,
      "bookmarkCount": 0
    },
    "versions": [
      {
        "versionNumber": "0.1",
        "sourceType": "SOURCE_FILES",
        "buildTag": "latest"
      }
    ],
    "defaultRunOptions": {
      "build": "latest",
      "timeoutSecs": 3600,
      "memoryMbytes": 1024
    },
    "exampleRunInput": {
      "body": "{\"urls\":[\"https://upload.wikimedia.org/wikipedia/commons/d/d1/En-uk-hello-6.ogg\"]}",
      "contentType": "application/json"
    },
    "categories": [
      "AI",
      "VIDEOS",
      "AUTOMATION"
    ],
    "isDeprecated": false,
    "title": "Speech to Text: Audio Transcriber, Whisper, SRT & VTT",
    "pictureUrl": "https://apify-image-uploads-prod.s3.us-east-1.amazonaws.com/e5eBfwJfZr4LIY9GC-actor-SogOChnbEL31XZWeO-e1oqNn3Nsx-audio-transcriber.png",
    "seoTitle": "Speech to Text & Audio Transcriber - Whisper, SRT, VTT",
    "seoDescription": "Transcribe audio to text with Whisper: speech to text for mp3, wav, mp4, webm, mov URLs or podcast RSS, output text, SRT, VTT. No API key. First 2 minutes free.",
    "pricingInfos": [
      {
        "pricingModel": "PAY_PER_EVENT",
        "pricingPerEvent": {
          "actorChargeEvents": {
            "audio-minute": {
              "eventTitle": "Audio minute transcribed",
              "eventDescription": "One minute of audio (rounded up per file, minimum 1; the first 2 minutes of every run are free) that was successfully transcribed. Files that fail to download, decode or transcribe are never charged.",
              "eventPriceUsd": 0.008
            }
          }
        },
        "createdAt": "2026-10-21T14:38:51.201Z",
        "startedAt": "2026-10-21T14:38:51.201Z",
        "apifyMarginPercentage": 0.2,
        "notifiedAboutChangeAt": "2026-10-21T15:00:35.378Z"
      },
      {
        "pricingModel": "PAY_PER_EVENT",
        "pricingPerEvent": {
          "actorChargeEvents": {
            "audio-minute": {
              "eventTitle": "Audio minute transcribed",
              "eventDescription": "One minute of audio (rounded up per file, minimum 1; the first 2 minutes of every run are free) that was successfully transcribed. Files that fail to download, decode or transcribe are never charged.",
              "eventTieredPricingUsd": {
                "FREE": {
                  "tieredEventPriceUsd": 0.008
                },
                "BRONZE": {
                  "tieredEventPriceUsd": 0.0072
                },
                "SILVER": {
                  "tieredEventPriceUsd": 0.0064
                },
                "GOLD": {
                  "tieredEventPriceUsd": 0.0056
                },
                "PLATINUM": {
                  "tieredEventPriceUsd": 0.0056
                },
                "DIAMOND": {
                  "tieredEventPriceUsd": 0.0056
                }
              }
            }
          }
        },
        "apifyMarginPercentage": 0.2,
        "createdAt": "2026-10-22T12:30:25.861Z",
        "startedAt": "2026-10-22T12:30:25.861Z",
        "notifiedAboutChangeAt": "2026-10-22T13:00:41.514Z"
      },
      {
        "pricingModel": "PAY_PER_EVENT",
        "pricingPerEvent": {
          "actorChargeEvents": {
            "audio-minute": {
              "eventTitle": "Audio minute transcribed",
              "eventDescription": "One minute of audio (rounded up per file, minimum 1; the first 2 minutes of every run are free) that was successfully transcribed. Files that fail to download, decode or transcribe are never charged.",
              "eventTieredPricingUsd": {
                "FREE": {
                  "tieredEventPriceUsd": 0.006
                },
                "BRONZE": {
                  "tieredEventPriceUsd": 0.0054
                },
                "SILVER": {
                  "tieredEventPriceUsd": 0.0048
                },
                "GOLD": {
                  "tieredEventPriceUsd": 0.0042
                },
                "PLATINUM": {
                  "tieredEventPriceUsd": 0.0042
                },
                "DIAMOND": {
                  "tieredEventPriceUsd": 0.0042
                }
              }
            }
          }
        },
        "apifyMarginPercentage": 0.2,
        "createdAt": "2026-10-24T02:01:00.865Z",
        "startedAt": "2026-10-24T02:01:00.000Z",
        "notifiedAboutChangeAt": "2026-10-24T02:30:31.990Z"
      }
    ],
    "notice": "NONE",
    "isCritical": false,
    "isGeneric": false,
    "hasNoDataset": false,
    "isSourceCodeHidden": true,
    "standbyUrl": null,
    "actorPermissionLevel": "LIMITED_PERMISSIONS",
    "readmeSummary": "## Audio & Video to Text - Whisper Transcription API (pennydata/audio-transcriber)\n\nTranscribes audio and video file URLs and podcast RSS feeds to searchable text and subtitle outputs using OpenAI Whisper (models: base and tiny) running inside the Actor; accepts common media formats (mp3, wav, m4a, ogg, flac, mp4, webm, mov), extracts audio from video with ffmpeg, performs automatic language detection and optional translation to English, and produces full transcripts, timestamped segments, per-file duration and status metadata, optional word-level timestamps, and subtitle files in SRT and VTT formats.\n\n## Use cases\n\n- Transcribe podcast RSS feeds into one transcript per episode for show notes and searchable archives.  \n- Generate SRT and VTT subtitle files from audio or video files for editors and publishing.  \n- Convert video files to text by extracting audio and transcribing speech.  \n- Produce timestamped segments and optional word-level timestamps for quote pulling, indexing, or alignment.  \n- Translate spoken content into English (speech-to-text translation).  \n- Integrate as a tool for AI agents via an MCP server.  \n- Drop-in compatibility with inputs used for other transcriber actors to migrate existing workflows.",
    "deploymentKey": "ssh-rsa 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 \n"
  }
}