Audio and Video to Transcript — timestamps, SRT, VTT

Give it URLs of audio or video files (MP3, M4A, WAV, FLAC, OGG, Opus, WebM, MP4, MOV); it returns the transcript with segment timestamps and, on request, SRT and VTT subtitles, detecting the language unless told. Use it on recordings, podcasts, meetings or videos the user has given you a file link for. Agents cannot listen: one call turns a media link into timed text you can quote, search or summarise, an English translation of speech in other languages on request, and pricing is per started minute of media, so an 11-second clip costs less than a cent.

Call it from an agent

Through Apify's MCP server (https://mcp.apify.com), tool call-actor:

{"actor": "hermeskd/audio-to-transcript", "input": {"urls": ["https://raw.githubusercontent.com/SYSTRAN/faster-whisper/master/tests/data/jfk.flac"], "language": "en"}, "callOptions": {"maxTotalChargeUsd": 0.05, "timeout": 3600}, "waitSecs": 30}

The call returns the run's status and its defaultDatasetId. Read the records with get-dataset-items:

{"datasetId": "<defaultDatasetId from the call>", "limit": 50}

As a dedicated tool, add https://mcp.apify.com?tools=hermeskd/audio-to-transcript to your MCP client. A short clip usually finishes inside the 30-second wait; a long recording takes longer (see Limits and run time), so when the call returns with the run still RUNNING, wait for it and then read the dataset. maxTotalChargeUsd caps what the run can charge: a file whose minutes would pass it is not transcribed and comes back as a charge_limit_reached record, uncharged.

Input

Field	Type	Required	Default	Meaning
urls	array of strings	yes	—	Media file URLs (MP3, M4A, WAV, FLAC, OGG, Opus, WebM, MP4, MOV), http or https, 1–20 per run, ≤ 500 MB and ≤ 120 minutes each.
language	string	no	auto	ISO 639-1 code to force the spoken language (99 languages, e.g. en, de, es, zh; haw for Hawaiian); auto detects it from the first speech.
formats	array of text · srt · vtt	no	["text"]	What to return inline, 1–3 of: text (the transcript and its timed segments), srt (SubRip subtitles), vtt (WebVTT subtitles).
translateToEnglish	boolean	no	false	Return an English translation instead of the source language — text, segments and subtitles alike; language still names the source language. Translation is Whisper base's own: good enough to follow the gist of common European languages, rough for others.

Every limit above is enforced in the input schema (minimum/maximum, maxItems) and again in code.

Output

One record per input URL.

Field	Meaning
url	The input URL.
ok	true when the file was transcribed; false with error.
language	The spoken language as an ISO 639-1 code: the one given, or the one detected from the first speech; null when no speech was found and none was given.
durationSec	The media's duration in seconds.
minutesCharged	Started minutes of media duration charged for this file (11 s is 1, 61 s is 2).
text	With formats text: the full transcript, segments joined by spaces. Media with no speech gives ok: true and an empty string, and is charged — the file was listened to.
segments	With formats text: the transcript as {start, end, text} segments in seconds from the file's start, in order, never overlapping, never past durationSec.
srt	With formats srt: the segments as SubRip subtitles.
vtt	With formats vtt: the segments as WebVTT subtitles.
error	{code, message} when ok is false.

Example record for the call above, as this Actor returned it for the same file in its build check on 2026-10-16:

{
  "url": "https://raw.githubusercontent.com/SYSTRAN/faster-whisper/master/tests/data/jfk.flac",
  "ok": true,
  "language": "en",
  "durationSec": 11.0,
  "minutesCharged": 1,
  "text": "And so my fellow Americans ask not what your country can do for you, ask what you can do for your country.",
  "segments": [
    {"start": 0.0, "end": 11.0, "text": "And so my fellow Americans ask not what your country can do for you, ask what you can do for your country."}
  ]
}

Events and prices

Pay per event; platform usage is included in the price, never passed through.

Event	Title	Charged when	FREE / BRONZE	SILVER	GOLD / PLATINUM / DIAMOND
audio-minute-transcribed	Audio minute transcribed	One started minute of media duration transcribed.	$0.008	$0.0072	$0.0064

Apify also charges its standard apify-actor-start event: $0.00005 per GB of run memory (2 events, $0.0001, at the default 2,048 MB). The minimum maximum-charge a caller can set is $0.02.

Worked example on the FREE tier: a 30-minute podcast episode and a 45-second voice note cost 30 × $0.008 + 1 × $0.008 = $0.248, plus $0.0001 for the start, $0.2481 in all. Minutes are counted from the media's duration, silence included; nothing is charged for a failed file.

Limits and run time

• 1–20 URLs per run, processed one after another; each file up to 500 MB and 120 minutes (a longer file is refused as too_long before it is decoded, uncharged).
• Each file has a download budget of 30 s plus 1 s per 2 MB of its size, so files download at 2 MB/s or faster; a download that sends nothing for 30 seconds is stopped. At most 2 requests a second go to one host.
• GitHub release links (github.com/…/releases/download/…) are refused with robots_disallowed: github.com's robots.txt disallows every user-agent it does not name (User-agent: * → Disallow: /), HermesBot included, and HermesBot obeys it. Put the file on raw.githubusercontent.com (a file committed to a repository) or your own storage and pass that URL.
• The first audio track is transcribed; a video's picture is ignored. The file's own container is read — playlists and manifests (M3U, HLS, DASH) are not media files and are refused.
• Speech is found by voice-activity detection and transcribed in windows of up to 28 seconds of speech by Whisper base; silence costs almost no processing. Segment times are accurate to about a second; words are not timed individually.
• Typical run time: the 11-second clip above in about 5–15 seconds, a third of it loading the model. Continuous speech takes about 13 seconds of one CPU core per minute of audio (12.7 s on a 28-minute audiobook reading, 13.4 s on a dense meeting), sparse speech (a meeting with pauses) about 10 (measured 2026-10-16 and 2026-10-17); the default 2,048 MB run has half a core, so it transcribes a minute of continuous speech in about half a minute, and a recording of more than about 60 minutes of continuous speech needs more memory (4,096 MB is one core, 8,192 MB two) or a run timeout above the default 3,600 seconds. Transcription runs one thread per core of the run's memory share (at least one, at most four). A file not finished within the run's time is timeout, uncharged.

Errors

Errors are records with ok: false and error.code; none is charged.

error.code	Meaning
download_failed	The URL did not return the file (status or network error), or the download was slower than its budget.
no_audio_stream	No decodable audio: the file has no audio track (a silent video), or it is not audio or video media at all (text, HTML, a playlist) — anything ffprobe cannot open as a single media file.
too_long	Over 120 minutes.
too_large	Over 500 MB.
unsupported_media	The file has an audio track, but its codec could not be decoded.
robots_disallowed	robots.txt forbids fetching the URL.
blocked_host	The host is on the deny-list (YouTube, TikTok, Instagram and other platforms whose terms forbid automated download), or resolves to a private or local address.
timeout	The file did not finish within the run's time budget.
internal_error	Unexpected failure; message carries the class.
charge_limit_reached	The run's maximum total charge could not pay for this file's minutes; it was not transcribed.
invalid_input	The run input passed the input schema but cannot be used (for example no URL at all); the message names the field. One record per input given, or one with url: null when none was given; nothing is processed.

The run fails only when every input failed with an Actor-side code (internal_error, timeout), so a broken Actor is visible. Every other run succeeds — including one where nothing was transcribed because of the caller's own inputs (bad URL, robots, deny-list, no audio, too long, invalid input, the charge limit), or where those and Actor-side failures are mixed.

Sources and terms

The source is the caller's media. Process only media you have the right to process. Fetching follows the Hermes fetch policy: robots.txt is obeyed for the user-agent HermesBot (and *), and a disallowed URL is refused without a request; platforms whose terms forbid automated access — YouTube, TikTok, Instagram among them — and people-search sites are on a deny-list and refused without a request; private and local addresses are refused, after DNS and on every redirect; the user-agent is HermesBot/1.0 (+https://apify.com/hermeskd); no login, cookies, credentials, CAPTCHA solving, evasion or proxies are used. The words spoken are returned to the caller as they are; no speaker is named and no voice is identified.

The models run inside the Actor; no audio leaves the run. Whisper base (OpenAI's weights, MIT licence) runs as the float32 ONNX export published by the sherpa-onnx project (k2-fsa, Apache-2.0), with Silero VAD (MIT) to find speech and FFmpeg to decode; each model file is checked against a pinned SHA-256 when the image is built.

Not affiliated

This Actor is not affiliated with OpenAI, the sherpa-onnx (k2-fsa) project, Silero or the FFmpeg project. Whisper, sherpa-onnx, Silero VAD and FFmpeg are used under their open-source licences. YouTube, TikTok and Instagram are named only to say they are refused.

Related Hermes Actors

• pdf-to-markdown — PDF documents to Markdown, with OCR for scanned pages.
• document-to-markdown — Word, PowerPoint, Excel and other office files to Markdown.
• image-to-text — text read from images by OCR.
• video-frames — frames and metadata from a video.
• image-upscale — image upscaling.
• url-to-markdown — a web page to Markdown.
• audio-video-convert — audio and video format conversion.

Changelog

• 1.0 (2026-10-16) — first release: speech in 99 languages to text with segment timestamps, SRT and WebVTT subtitles, English translation; Whisper base with voice-activity detection.