{ "data": { "id": "z3OJfmBPQQz9svFFB", "userId": "wUWj0zAfdzaiGiVU8", "name": "media-transcriber", "username": "sauliusautomatesit", "description": "Audio transcription and video transcription API: transcribe audio, video, MP3, MP4, podcasts to text with Whisper speech to text. Podcast transcription from RSS feeds, meeting and interview transcription, voice to text, SRT/VTT subtitles, RAG chunks. From $0.01 per audio minute; silence is free.", "isPublic": true, "createdAt": "2026-08-13T19:10:10.658Z", "modifiedAt": "2026-10-10T20:00:56.077Z", "taggedBuilds": { "latest": { "buildId": "qp2dm65fDatoZCEU3", "finishedAt": "2026-10-06T18:53:15.765Z", "buildNumberInt": 10400016, "buildNumber": "1.4.16" }, "beta": { "buildId": "An5bywnWRS0bSAeWk", "finishedAt": "2026-10-04T21:58:36.880Z", "buildNumberInt": 10400012, "buildNumber": "1.4.12" }, "recovery": { "buildId": "1AdAlgzuoLyINIaTC", "finishedAt": "2026-09-06T17:38:42.376Z", "buildNumberInt": 10100001, "buildNumber": "1.1.1" }, "notice": { "buildId": "yODUOmWlTOHrEUhGW", "finishedAt": "2026-09-06T19:18:04.122Z", "buildNumberInt": 10100002, "buildNumber": "1.1.2" }, "growth": { "buildId": "wNErpeXdwRFGRG8RZ", "finishedAt": "2026-09-09T14:23:03.017Z", "buildNumberInt": 10200002, "buildNumber": "1.2.2" }, "release-20260910": { "buildId": "Atb8fV4ue9C7Q4npE", "finishedAt": "2026-09-10T17:11:49.306Z", "buildNumberInt": 10300001, "buildNumber": "1.3.1" }, "hardening-20260910": { "buildId": "jupdEFBeQp5zh5mW3", "finishedAt": "2026-09-10T19:23:46.488Z", "buildNumberInt": 10400001, "buildNumber": "1.4.1" }, "completion-20260910": { "buildId": "fb3NZiyBLcuqgsrAZ", "finishedAt": "2026-09-10T20:56:14.133Z", "buildNumberInt": 10400002, "buildNumber": "1.4.2" }, "reliability-20260913": { "buildId": "byr3c5mimJpQtzYlf", "finishedAt": "2026-09-13T19:34:40.704Z", "buildNumberInt": 10400003, "buildNumber": "1.4.3" }, "listing-20260913": { "buildId": "iZ3UBMx8zwxTj3qEa", "finishedAt": "2026-09-13T19:39:49.677Z", "buildNumberInt": 10400004, "buildNumber": "1.4.4" }, "monitorname-20260925": { "buildId": "HuB6vHQO4gqKn5hye", "finishedAt": "2026-09-25T21:23:00.309Z", "buildNumberInt": 10400006, "buildNumber": "1.4.6" }, "listing-20261002": { "buildId": "w8dW5h2WUxa88Uv8X", "finishedAt": "2026-10-02T13:23:43.967Z", "buildNumberInt": 10400007, "buildNumber": "1.4.7" } }, "stats": { "totalBuilds": 29, "totalRuns": 626, "totalUsers": 69, "totalUsers7Days": 5, "totalUsers30Days": 13, "totalUsers90Days": 53, "lastRunStartedAt": "2026-10-23T14:08:40.312Z", "actorReviewCount": 0, "actorReviewRating": 0, "bookmarkCount": 0, "publicActorRunStats30Days": { "ABORTED": 0, "FAILED": 11, "SUCCEEDED": 40, "TIMED-OUT": 0, "TOTAL": 51 } }, "versions": [ { "versionNumber": "1.0", "sourceType": "SOURCE_FILES", "buildTag": "latest" }, { "versionNumber": "1.1", "sourceType": "SOURCE_FILES", "buildTag": "recovery" }, { "versionNumber": "1.2", "sourceType": "SOURCE_FILES", "buildTag": "growth" }, { "versionNumber": "1.3", "sourceType": "SOURCE_FILES", "buildTag": "release-20260910" }, { "versionNumber": "1.4", "sourceType": "SOURCE_FILES", "buildTag": "listing-20261002" } ], "defaultRunOptions": { "build": "latest", "timeoutSecs": 7200, "memoryMbytes": 4096 }, "exampleRunInput": { "body": "{ \"helloWorld\": 123 }", "contentType": "application/json; charset=utf-8" }, "categories": [ "AI", "VIDEOS", "FOR_CREATORS" ], "isDeprecated": false, "title": "Speech to Text API: Audio to Text & Video to Text, Whisper", "pictureUrl": "https://apify-image-uploads-prod.s3.us-east-1.amazonaws.com/wUWj0zAfdzaiGiVU8-actor-z3OJfmBPQQz9svFFB-1JO35jJ1fu-transcriber-icon.png", "seoTitle": "Speech to Text API & Audio to Text API (Whisper)", "seoDescription": "Speech to text API for audio, video, MP3 and podcast URLs. Whisper transcription with SRT/VTT subtitles, timestamps and RAG chunks. From $0.01/minute.", "pricingInfos": [ { "minimalMaxTotalChargeUsd": null, "pricingModel": "PAY_PER_EVENT", "isPriceChangeNotificationSuppressed": false, "pricingPerEvent": { "actorChargeEvents": { "apify-actor-start": { "eventTitle": "Actor Start", "eventDescription": "Charged when the Actor starts running. Number of events charged depends on Actor memory (one event per GB, minimum one event).", "isOneTimeEvent": true, "eventPriceUsd": 0.00005 }, "audio_minute": { "eventTitle": "Audio minute", "eventDescription": "Charged per minute of audio successfully transcribed (rounded up).", "isOneTimeEvent": false, "eventPriceUsd": 0.04, "isPrimaryEvent": true } } }, "startedAt": "2026-08-13T22:30:52.997Z", "createdAt": "2026-08-13T22:30:53.240Z", "apifyMarginPercentage": 0.2 }, { "minimalMaxTotalChargeUsd": null, "pricingModel": "PAY_PER_EVENT", "isPriceChangeNotificationSuppressed": false, "pricingPerEvent": { "actorChargeEvents": { "audio_minute": { "eventTitle": "Audio minute", "eventDescription": "Charged per minute of audio successfully transcribed (rounded up).", "isOneTimeEvent": false, "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.04 }, "BRONZE": { "tieredEventPriceUsd": 0.038 }, "SILVER": { "tieredEventPriceUsd": 0.036 }, "GOLD": { "tieredEventPriceUsd": 0.034 }, "PLATINUM": { "tieredEventPriceUsd": 0.034 }, "DIAMOND": { "tieredEventPriceUsd": 0.034 } }, "isPrimaryEvent": true }, "apify-actor-start": { "eventTitle": "Actor Start", "eventDescription": "Charged when the Actor starts running. Number of events charged depends on Actor memory (one event per GB, minimum one event).", "isOneTimeEvent": true, "eventPriceUsd": 0.00005 } } }, "startedAt": "2026-08-17T13:20:50.775Z", "createdAt": "2026-08-17T13:20:47.757Z", "apifyMarginPercentage": 0.2, "notifiedAboutChangeAt": "2026-08-19T08:06:28.160Z" }, { "pricingModel": "PAY_PER_EVENT", "apifyMarginPercentage": 0.2, "createdAt": "2026-09-10T19:46:10.526Z", "startedAt": "2026-09-24T19:51:10.403Z", "isPriceChangeNotificationSuppressed": false, "forceContainsSignificantPriceChange": true, "reasonForChange": "Match recognition pricing to processing cost: Basic (base), Quality (small), Max (medium). All existing output formats remain included.", "pricingPerEvent": { "actorChargeEvents": { "apify-actor-start": { "eventTitle": "Actor Start", "eventDescription": "Charged when the Actor starts running. Number of events charged depends on Actor memory (one event per GB, minimum one event).", "isOneTimeEvent": true, "eventPriceUsd": 0.00005 }, "audio_minute_basic": { "eventTitle": "Basic audio minute", "eventDescription": "One minute of complete delivered speech, rounded up separately for each recording.", "isOneTimeEvent": false, "isPrimaryEvent": true, "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.035 }, "BRONZE": { "tieredEventPriceUsd": 0.03325 }, "SILVER": { "tieredEventPriceUsd": 0.0315 }, "GOLD": { "tieredEventPriceUsd": 0.02975 }, "PLATINUM": { "tieredEventPriceUsd": 0.02975 }, "DIAMOND": { "tieredEventPriceUsd": 0.02975 } } }, "audio_minute_quality": { "eventTitle": "Quality audio minute", "eventDescription": "One minute of complete delivered speech, rounded up separately for each recording.", "isOneTimeEvent": false, "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.06 }, "BRONZE": { "tieredEventPriceUsd": 0.057 }, "SILVER": { "tieredEventPriceUsd": 0.054 }, "GOLD": { "tieredEventPriceUsd": 0.051 }, "PLATINUM": { "tieredEventPriceUsd": 0.051 }, "DIAMOND": { "tieredEventPriceUsd": 0.051 } } }, "audio_minute_max": { "eventTitle": "Max audio minute", "eventDescription": "One minute of complete delivered speech, rounded up separately for each recording.", "isOneTimeEvent": false, "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.12 }, "BRONZE": { "tieredEventPriceUsd": 0.114 }, "SILVER": { "tieredEventPriceUsd": 0.108 }, "GOLD": { "tieredEventPriceUsd": 0.102 }, "PLATINUM": { "tieredEventPriceUsd": 0.102 }, "DIAMOND": { "tieredEventPriceUsd": 0.102 } } }, "audio_minute": { "eventTitle": "Audio minute", "eventDescription": "Charged per minute of audio successfully transcribed (rounded up).", "isOneTimeEvent": false, "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.04 }, "BRONZE": { "tieredEventPriceUsd": 0.038 }, "SILVER": { "tieredEventPriceUsd": 0.036 }, "GOLD": { "tieredEventPriceUsd": 0.034 }, "PLATINUM": { "tieredEventPriceUsd": 0.034 }, "DIAMOND": { "tieredEventPriceUsd": 0.034 } }, "isPrimaryEvent": false } } }, "notifiedAboutFutureChangeAt": "2026-09-10T19:46:31.519Z", "notifiedAboutChangeAt": "2026-09-24T20:05:57.904Z" }, { "pricingModel": "PAY_PER_EVENT", "apifyMarginPercentage": 0.2, "isPriceChangeNotificationSuppressed": false, "reasonForChange": "Price cut: Basic $0.01, Quality $0.02, Max $0.04 per audio minute. Nothing else changes.", "pricingPerEvent": { "actorChargeEvents": { "apify-actor-start": { "eventTitle": "Actor Start", "eventDescription": "Charged when the Actor starts running. Number of events charged depends on Actor memory (one event per GB, minimum one event).", "isOneTimeEvent": true, "eventPriceUsd": 0.00005 }, "audio_minute_basic": { "eventTitle": "Basic audio minute", "eventDescription": "One minute of complete delivered speech, rounded up separately for each recording.", "isOneTimeEvent": false, "isPrimaryEvent": true, "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.01 }, "BRONZE": { "tieredEventPriceUsd": 0.0095 }, "SILVER": { "tieredEventPriceUsd": 0.009 }, "GOLD": { "tieredEventPriceUsd": 0.0085 }, "PLATINUM": { "tieredEventPriceUsd": 0.0085 }, "DIAMOND": { "tieredEventPriceUsd": 0.0085 } } }, "audio_minute_quality": { "eventTitle": "Quality audio minute", "eventDescription": "One minute of complete delivered speech, rounded up separately for each recording.", "isOneTimeEvent": false, "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.02 }, "BRONZE": { "tieredEventPriceUsd": 0.019 }, "SILVER": { "tieredEventPriceUsd": 0.018 }, "GOLD": { "tieredEventPriceUsd": 0.017 }, "PLATINUM": { "tieredEventPriceUsd": 0.017 }, "DIAMOND": { "tieredEventPriceUsd": 0.017 } } }, "audio_minute_max": { "eventTitle": "Max audio minute", "eventDescription": "One minute of complete delivered speech, rounded up separately for each recording.", "isOneTimeEvent": false, "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.04 }, "BRONZE": { "tieredEventPriceUsd": 0.038 }, "SILVER": { "tieredEventPriceUsd": 0.036 }, "GOLD": { "tieredEventPriceUsd": 0.034 }, "PLATINUM": { "tieredEventPriceUsd": 0.034 }, "DIAMOND": { "tieredEventPriceUsd": 0.034 } } }, "audio_minute": { "eventTitle": "Audio minute", "eventDescription": "Charged per minute of audio successfully transcribed (rounded up).", "isOneTimeEvent": false, "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.01 }, "BRONZE": { "tieredEventPriceUsd": 0.0095 }, "SILVER": { "tieredEventPriceUsd": 0.009 }, "GOLD": { "tieredEventPriceUsd": 0.0085 }, "PLATINUM": { "tieredEventPriceUsd": 0.0085 }, "DIAMOND": { "tieredEventPriceUsd": 0.0085 } }, "isPrimaryEvent": false } } }, "createdAt": "2026-10-06T06:42:07.750Z", "startedAt": "2026-10-06T06:42:07.579Z", "notifiedAboutChangeAt": "2026-10-06T07:00:31.728Z" }, { "pricingModel": "PAY_PER_EVENT", "apifyMarginPercentage": 0.2, "isPriceChangeNotificationSuppressed": false, "reasonForChange": "Basic $0.02, Quality $0.04, Max $0.08 per audio minute. Nothing else changes.", "pricingPerEvent": { "actorChargeEvents": { "apify-actor-start": { "eventTitle": "Actor Start", "eventDescription": "Charged when the Actor starts running. Number of events charged depends on Actor memory (one event per GB, minimum one event).", "isOneTimeEvent": true, "eventPriceUsd": 0.00005 }, "audio_minute_basic": { "eventTitle": "Basic audio minute", "eventDescription": "One minute of complete delivered speech, rounded up separately for each recording.", "isOneTimeEvent": false, "isPrimaryEvent": true, "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.02 }, "BRONZE": { "tieredEventPriceUsd": 0.019 }, "SILVER": { "tieredEventPriceUsd": 0.018 }, "GOLD": { "tieredEventPriceUsd": 0.017 }, "PLATINUM": { "tieredEventPriceUsd": 0.017 }, "DIAMOND": { "tieredEventPriceUsd": 0.017 } } }, "audio_minute_quality": { "eventTitle": "Quality audio minute", "eventDescription": "One minute of complete delivered speech, rounded up separately for each recording.", "isOneTimeEvent": false, "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.04 }, "BRONZE": { "tieredEventPriceUsd": 0.038 }, "SILVER": { "tieredEventPriceUsd": 0.036 }, "GOLD": { "tieredEventPriceUsd": 0.034 }, "PLATINUM": { "tieredEventPriceUsd": 0.034 }, "DIAMOND": { "tieredEventPriceUsd": 0.034 } } }, "audio_minute_max": { "eventTitle": "Max audio minute", "eventDescription": "One minute of complete delivered speech, rounded up separately for each recording.", "isOneTimeEvent": false, "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.08 }, "BRONZE": { "tieredEventPriceUsd": 0.076 }, "SILVER": { "tieredEventPriceUsd": 0.072 }, "GOLD": { "tieredEventPriceUsd": 0.068 }, "PLATINUM": { "tieredEventPriceUsd": 0.068 }, "DIAMOND": { "tieredEventPriceUsd": 0.068 } } }, "audio_minute": { "eventTitle": "Audio minute", "eventDescription": "Charged per minute of audio successfully transcribed (rounded up).", "isOneTimeEvent": false, "eventTieredPricingUsd": { "FREE": { "tieredEventPriceUsd": 0.02 }, "BRONZE": { "tieredEventPriceUsd": 0.019 }, "SILVER": { "tieredEventPriceUsd": 0.018 }, "GOLD": { "tieredEventPriceUsd": 0.017 }, "PLATINUM": { "tieredEventPriceUsd": 0.017 }, "DIAMOND": { "tieredEventPriceUsd": 0.017 } }, "isPrimaryEvent": false } } }, "createdAt": "2026-10-10T20:00:56.094Z", "startedAt": "2026-10-24T20:10:55.936Z", "notifiedAboutFutureChangeAt": "2026-10-10T20:01:17.110Z" } ], "notice": "NONE", "isCritical": false, "isGeneric": false, "hasNoDataset": false, "isSourceCodeHidden": true, "standbyUrl": null, "actorPermissionLevel": "LIMITED_PERMISSIONS", "readmeSummary": "## Speech to Text API: Audio to Text & Video to Text (Media Transcriber)\n\nA speech-to-text Actor that transcribes audio and video links and podcast feeds using Whisper models inside the Actor container; it produces full transcripts, timestamped segments, SRT/VTT subtitles, Markdown exports and source-linked RAG chunks (chunked, timestamped text with citation links) in 90+ languages with optional speech-to-English translation. Designed for direct HTTP(S) media files, podcast RSS/Atom feeds, YouTube (best-effort) and other sites via yt-dlp with proxy support, the Actor performs auto language detection, processes long recordings in five-minute processing blocks while preserving timestamps across the file, supports multiple model tiers for accuracy/speed tradeoffs, offers per-word timestamping and configurable chunking/overlap for RAG-ready output, and runs recognition locally (no third-party transcription service).\n\n## Use cases\n\n- Automatically transcribe new podcast episodes and skip previously processed episodes (monitoring/checkpointing).\n- Produce SRT and VTT captions for video accessibility and SEO.\n- Transcribe interviews, lectures, briefings and call recordings for research or journalism.\n- Create timestamped, source-linked RAG chunks for search and retrieval / audio knowledge bases.\n- Translate foreign-language speech into English for localization or review.", "deploymentKey": "ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQDr8eV1K4ZmqnBpWFAWnAUtr8XycXkrosLCuGDSf/jVcWHL9fZcqf7gMrJ5YObFkLm6MdWTxcsEsRNdHi+ChLhnnLkhJVZ9lAOYDwP0TN1dult/jf88I6lTd5UC+KyVRJoXB/GZl6sLSCopdPVqa5/RkHL+viqBPaLlJUEB3UFdSrCEn0hQS77xM+twlgPcyonsdEEyef9h4585JM5UD0DhPDnIGekchkE81accYQt5CzClNWYDabnLGsOSXZBWXCav7bi1WCn1vH7Xe8ey40aSjg9wc/nmxrJmiJlVOxzgVPLKLlp0hmlBEzTrlM2x3Nhk0xzaQKwCvoYXbRDQ4qz9 \n" } }