{"name":"audio-transcription","id":"sfoln/audio-transcription","title":"Audio Transcription API – Speech to Text","description":"Transcribe audio and video files (MP3, WAV, M4A, MP4…) to text by URL with Mistral Voxtral: language detection, optional segment timestamps and speaker labels. $10.50 per 1,000 audio minutes, billed per started minute; failed files are free.","version":"0.1","status":"ready","family":{"id":"documents-media-ai","name":"Documents & media","description":"PDF and office documents to Markdown or JSON, OCR, audio and podcast transcription, YouTube transcripts, summaries and video metadata.","actors":8},"categories":["AI","DEVELOPER_TOOLS","AUTOMATION"],"availability":"on_request","seoTitle":"Speech to Text API – $10.50 per 1,000 Audio Minutes","seoDescription":"Audio transcription API: turn MP3, WAV, M4A and MP4 files into text with timestamps and speaker labels. $10.50 per 1,000 minutes; failed files are free.","summary":"Audio Transcription API – Speech to Text transcribes podcasts, interviews, meetings, voice notes, webinars and videos to text in bulk. Give the Actor direct URLs of audio or video files and get one transcript per file with detected language, duration and word count — plus optional segment timestamps and speaker labels. Transcription is performed by Mistral Voxtral Mini Transcribe 2, a speech model with strong accuracy across major languages and files of up to about 3 hours.","pricing":{"model":"pay-per-event","currency":"USD","billedBy":"Apify","freePlanMaxItemsPerRun":5,"events":[{"name":"transcription-minute","title":"Transcribed audio minute","description":"Charged per started minute of audio transcribed (a 3 min 20 s file = 4 events).","priceUsd":0.0105}]},"input":{"description":"List publicly reachable audio or video file URLs. Each file produces one dataset record with the transcript.","required":["audioUrls"],"fields":[{"name":"audioUrls","title":"Audio / video URLs","type":"array","required":true,"description":"Direct, public URLs of audio or video files (MP3, WAV, M4A, FLAC, OGG, MP4, MOV, WEBM…), one per line. Up to about 3 hours per file. Page URLs (e.g. YouTube watch pages) are not supported. Accounts on the Apify free plan can process up to 5 files per run.","prefill":["https://docs.mistral.ai/audio/obama.mp3"],"editor":"stringList"},{"name":"language","title":"Language","type":"string","required":false,"description":"Optional ISO 639-1 language code of the speech (e.g. en, de, fr, es). Improves accuracy; leave empty for automatic detection.","editor":"textfield"},{"name":"timestamps","title":"Segment timestamps","type":"boolean","required":false,"description":"Return the transcript split into segments with start/end times in seconds.","default":false},{"name":"diarize","title":"Speaker labels","type":"boolean","required":false,"description":"Label segments by speaker (speaker_1, speaker_2, …). Implies segment timestamps.","default":false},{"name":"maxFileSizeMb","title":"Max file size (MB)","type":"integer","required":false,"description":"Files larger than this are skipped without charge.","default":100,"minimum":1,"maximum":1024},{"name":"maxFiles","title":"Max files","type":"integer","required":false,"description":"Safety cap on the number of files processed in this run.","default":100,"minimum":1,"maximum":5000},{"name":"concurrency","title":"Concurrency","type":"integer","required":false,"description":"Files transcribed in parallel.","default":3,"minimum":1,"maximum":5},{"name":"includeRaw","title":"Include raw upstream response","type":"boolean","required":false,"description":"Attach the unmodified transcription response to each record.","default":false}]},"exampleInput":{"audioUrls":["https://docs.mistral.ai/audio/obama.mp3"]},"outputFields":[{"name":"input","type":"string","title":"Input","description":"URL as submitted."},{"name":"url","type":"string","title":"URL"},{"name":"language","type":"string | null","title":"Language","description":"Detected (or requested) language code."},{"name":"text","type":"string","title":"Transcript"},{"name":"durationSecs","type":"number","title":"Duration (s)"},{"name":"billedMinutes","type":"integer","title":"Billed minutes","description":"Started minutes charged as transcription-minute events."},{"name":"wordCount","type":"integer","title":"Words"},{"name":"segmentCount","type":"integer","title":"Segments"},{"name":"segments","type":"array","title":"Segments","description":"[{ start, end, text, speaker }] — only with timestamps or diarize."},{"name":"model","type":"string","title":"Model"},{"name":"fileSizeBytes","type":"integer","title":"File size (bytes)","description":"Size the server reported for the file; on skipped_invalid records with error code file_too_large."},{"name":"estimatedMinutes","type":"integer","title":"Estimated minutes","description":"Estimated length in started minutes (from the file size); on records refused because of the free-plan length limit or the remaining budget."},{"name":"warnings","type":"array","title":"Warnings"},{"name":"status","type":"string","title":"Status","description":"ok | not_found | error | skipped_invalid | skipped_budget | skipped_free_plan","example":"ok"},{"name":"charged","type":"boolean","title":"Charged"},{"name":"source","type":"string","title":"Source"},{"name":"fetchedAt","type":"string","title":"Fetched at"}],"outputExample":{"input":"https://docs.mistral.ai/audio/obama.mp3","url":"https://docs.mistral.ai/audio/obama.mp3","language":"en","text":"This week, I traveled to Chicago to deliver my final farewell address to the nation, ...","durationSecs":203,"billedMinutes":4,"wordCount":525,"segmentCount":33,"segments":[{"start":0.8,"end":8.1,"text":"This week, I traveled to Chicago to deliver my final farewell address to the nation, following in the tradition of presidents before me.","speaker":null}],"model":"voxtral-mini-latest","status":"ok","charged":true,"chargedEvent":"transcription-minute","source":"mistral-voxtral","fetchedAt":"2026-10-14T10:00:00.000Z"},"faq":[],"mcpExamplePrompt":"Transcribe https://docs.mistral.ai/audio/obama.mp3 with segment timestamps and give me a short summary of what is said.","related":["youtube-transcript-summary","podcast-scraper","pdf-ocr-markdown","document-to-json"],"urls":{"site":"https://www.sfoln.com/actors/audio-transcription/","siteJson":"https://www.sfoln.com/actors/audio-transcription.json","siteMarkdown":"https://www.sfoln.com/actors/audio-transcription.md","runSync":"https://api.apify.com/v2/actors/sfoln~audio-transcription/run-sync-get-dataset-items","runAsync":"https://api.apify.com/v2/actors/sfoln~audio-transcription/runs","mcp":"https://mcp.apify.com?tools=sfoln/audio-transcription","requestAccess":"mailto:contact@sfoln.com?subject=Access%20request%3A%20Audio%20Transcription%20API%20%E2%80%93%20Speech%20to%20Text%20(sfoln%2Faudio-transcription)&body=Please%20publish%20audio-transcription.%20What%20we%20plan%20to%20use%20it%20for%3A"},"publisher":{"name":"SFOLN LLC","apifyUsername":"sfoln","url":"https://www.sfoln.com","apifyProfile":"https://apify.com/sfoln","email":"contact@sfoln.com"},"generatedAt":"2026-10-22T04:28:58.477Z"}