Pricing

from $2.10 / 1,000 audio minutes

Try for free

Go to Apify Store

Speech to Text: Audio, Video & Podcast Transcriber

Try for free

Speech to text with Whisper, no API key needed: transcribe audio, video and podcast RSS episodes to text, SRT and VTT subtitles and timestamped JSON segments. 99 languages. Optional own Groq or OpenAI key.

Pricing

from $2.10 / 1,000 audio minutes

Rating

0.0

(0)

Developer

Rod Services

Actor stats

Bookmarked

Total users

Monthly active users

19 days ago

Last modified

Categories

Videos

type

Optional

Only set to message for the notice pushed when no API key is given.

Type:string

sourceUrl

Optional

Media URL, RSS enclosure URL or key-value store record URL.

Type:string | null

sourceType

Optional

Type:string

Options:

urluploadkeyValueStorerss

title

Optional

Episode title from RSS, media title tag or file name.

Type:string | null

feedTitle

Optional

Type:string | null

feedUrl

Optional

Type:string | null

episodeUrl

Optional

Type:string | null

publishedAt

Optional

Type:string | null

fileName

Optional

Type:string | null

fileSizeBytes

Optional

Type:integer | null

durationSeconds

Optional

Duration of the source media.

Type:number | null

transcribedSeconds

Optional

Seconds of audio sent for transcription, after maxDurationMinutes.

Type:number | null

language

Optional

ISO 639-1 code, detected or from the hint.

Type:string | null

text

Optional

Type:string

segments

Optional

Type:object[]

segmentsCount

Optional

Type:integer

wordCount

Optional

Type:integer

srtUrl

Optional

Type:string | null

vttUrl

Optional

Type:string | null

txtUrl

Optional

Type:string | null

jsonUrl

Optional

Type:string | null

provider

Optional

Type:string | null

model

Optional

Type:string | null

translatedToEnglish

Optional

Type:boolean

timestampsApproximate

Optional

Type:boolean

chunksCount

Optional

Type:integer

chunks

Optional

Chunk plan, only in dry runs.

Type:array | null

billedMinutes

Optional

Type:integer

dryRun

Optional

Type:boolean

warnings

Optional

Type:string[]

error

Optional

Error for a failed file, or true for an input-error help item.

Type:string | boolean | null

processedAt

Optional

Type:string | null

processingSecs

Optional

Type:number | null

errorCode

Optional

Input error code (help item only).

Type:string | null

message

Optional

Input error message (help item only).

Type:string | null

howToFix

Optional

How to fix the input (help item only).

Type:string | null

apiKeySource

Optional

hosted when the Actor's shared Groq key was used, own for your key, none for dry runs

Type:string | null

Audio & Video to Text

donjuan_mime/audio-video-to-text

Transcribes video and audio files into plain text and subtitle formats (TXT, SRT, VTT, TSV, JSON) using OpenAI's Whisper model. Supports preloaded tiny, base, and small models.

Donjuan

105

Audio Transcriber — Speech to Text (Whisper)

viralanalyzer/audio-transcriber

Transcribe audio to text with Whisper running locally — no API key. Give any media URL (podcast, TikTok, Instagram, YouTube, or a direct audio file) and get text, timestamped segments, SRT subtitles and auto-detected language. Pay per minute transcribed.

viralanalyzer

Facebook video reel transcript

linen_snack/facebook-video-reel-transcript

Effortlessly convert any public Facebook reels videos into accurate text, subtitles, or translations with this powerful OpenAI Whisper API actor.

ius iyb

Video Transcriber - Video & Audio to Text Transcript

marielise.dev/video-transcriber-ultimate

Transcribe any video or audio URL to text. Full transcript, timestamped segments, SRT subtitles, word timings. YouTube, Vimeo, SoundCloud, direct media links. Whisper AI, 50+ languages, no API keys. $0.02 per minute.

Marielise

538

Audio Transcriber - Speech to Text

parseforge/audio-transcriber

Transcribes audio files from URL or upload into text with timestamps, language, and confidence. Supports WAV, MP3, AIFF, AAC, OGG, FLAC, and more.

ParseForge

160

5.0

(1)

Audio & Video Transcription (Whisper) for AI Agents

tinplatelabs/transcriber

Transcribe your audio and video files with Whisper: text, timestamped segments, optional word timings, language detection, translation to English, and SRT/VTT subtitle files. MP3, M4A, WAV, MP4, WebM and more from URLs or key-value stores. Priced per audio minute.

tinplatelabs

Audio & Video Transcriber — Speech to Text, SRT/VTT, Podcasts

steadyscrape/audio-video-transcriber

Speech to text for any audio or video file link (MP3, MP4 and more) or podcast feed: transcripts with timestamps, SRT and WebVTT subtitles. 99 languages auto-detected, translation to English, word timestamps. AI transcription with Whisper inside: no API key, no speech no charge.

Steady Scrape

Audio & Video Transcriber (Whisper): MP3, MP4, Podcasts to Text

pavel.tashev/audio-video-transcriber

Transcribe audio and video to text with Whisper: MP3 to text, MP4 transcription, podcast transcripts from an RSS feed, meeting recordings. Timestamps, SRT and VTT subtitles, 99 languages, no API key. Never charges for a failed or empty result.

Pavel Tashev

Transcribe Zoom Meeting to Text — Bulk Meeting Transcription

sian.agency/transcribe-zoom-meeting-to-text

Transcribe Zoom recordings to text in bulk. Speaker labels for host and participants, word-level timestamps, SRT/VTT export. 99+ languages. Try free.

SIÁN OÜ

Video & Audio Transcriber · Whisper Speech-to-Text, SRT & VTT

blackfalcondata/video-audio-transcriber

Whisper speech-to-text for any video, audio or podcast URL: full transcript with timestamped segments plus SRT/VTT subtitles, 99+ languages auto-detected. Works on YouTube and TikTok links, podcast RSS feeds and direct media files with no API key needed.