🚫 Social media links (Instagram, TikTok, YouTube Shorts, Facebook) are NOT supported and will be automatically rejected. Use our specialized actors linked in the description above.

✅ Valid: https://example.com/podcast.mp3, https://cdn.example.com/meeting.wav ❌ Invalid: https://www.instagram.com/reel/..., https://www.tiktok.com/@user/video/...

Supported Formats: MP3, WAV, FLAC, AAC, OPUS, OGG, M4A, MP4, MPEG, MOV, WebM Max file size: 1GB

Type:array

Upload Audio File or Video to Text

audioFiles

Optional

Upload audio or video files directly from your computer (or paste a URL). Each upload is stored in your key-value store and processed the same way as a direct URL.

Supported Formats: MP3, WAV, FLAC, AAC, OPUS, OGG, M4A, MP4, MPEG, MOV, WebM Max file size: 1GB per file

You can mix this with Audio/Video URLs above — both lists are processed together.

Type:array

Language (Optional)

language

Optional

Language spoken in the audio. Leave as 'Auto-detect' for automatic language detection.

Type:string

Default:auto

Options:

autoenglishchinesegermanspanishrussiankoreanfrenchjapaneseportugueseturkishpolishcatalandutcharabicswedishitalianindonesianhindifinnishvietnamesehebrewukrainiangreekmalayczechromaniandanishhungariantamilnorwegianthaiurducroatianbulgarianlithuanianlatinmaorimalayalamwelshslovaktelugupersianlatvianbengaliserbianazerbaijanisloveniankannadaestonianmacedonianbretonbasqueicelandicarmeniannepalimongolianbosniankazakhalbanianswahiligalicianmarathipunjabisinhalakhmershonayorubasomaliafrikaansoccitangeorgianbelarusiantajiksindhigujaratiamharicyiddishlaouzbekfaroesehaitian creolepashtoturkmennynorskmaltesesanskritluxembourgishmyanmartibetantagalogmalagasyassamesetatarhawaiianlingalahausabashkirjavanesesundanesecantonese

🔄 Translate to English (PAID)

translateToEnglish

Optional

Translate non-English audio into English. Additional charges apply for translation service.

Type:boolean

Default:false

🇪🇺 EU-Based Processing (PAID)

useEuServers

Optional

Process data within the EU for GDPR compliance. Higher processing rates apply for EU servers.

Type:boolean

Default:false

🎤 Speaker Diarization (PAID)

speakerDiarization

Optional

Identify and label different speakers in the audio (e.g., SPEAKER_00, SPEAKER_01). Perfect for meetings, interviews, and multi-person conversations. Additional charges apply.

Type:boolean

Default:false

Transcribe Voice Memo to Text — Speaker Labels & Timestamps

sian.agency/transcribe-voice-memo-to-text

Transcribe iPhone and Android voice memos to text. Speaker labels, word-level timestamps, SRT/VTT. Bulk upload, 99+ languages. Try free.

SIÁN OÜ

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

Transcribe Podcast to Text — Show Notes, SRT & Timestamps

sian.agency/transcribe-podcast-to-text

Transcribe podcast episodes to text in bulk. Speaker labels for hosts and guests, word-level timestamps, SRT/VTT for show notes. 99+ languages.

SIÁN OÜ

Transcribe Interview to Text — for Journalists & Researchers

sian.agency/transcribe-interview-to-text

Transcribe interviews and recorded conversations to text. Speaker labels for interviewer and guest, word-level timestamps, SRT/VTT. Try free.

SIÁN OÜ

Instagram To Text

truefetch/instagram-to-text

AI-transcribe any Instagram reel, story, or video — timestamped captions, speaker diarization, and translation into 100+ languages from a single pasted link. $0.30 per video.

TrueFetch

Video To Text

truefetch/video-to-text

Transcribe videos from 1,000+ platforms to text — auto language detection, timestamps, subtitle file download, and translation to 100+ languages. No file uploads. $0.30 per video.

TrueFetch

169

1.9

Speech To Text

vivid_astronaut/speech-to-text

Convert speech to text with high accuracy using Azure AI. Supports 100+ languages, speaker detection, and timestamps. Perfect for transcription, subtitles, and voice-to-text applications.

Fabio Suizu

Instagram Youtube Transcripts With Speaker Labels Full Account

transcriptdl/instagram-youtube-transcripts-with-speaker-labels-full-account

Verified 99.4% Success. BULK generate transcripts with speaker diarization from Instagram Reels & YouTube videos. Automatically identifies speakers, outputs SRT/VTT subtitles, timestamps & full text. Perfect for podcasts, interviews & meetings. Bulk processing supported.

Transcript Downloader

Hugging Face Audio AI

alizarin_refrigerator-owner/hugging-face-audio-ai

Audio w/Hugging Face models speech recognition, text-to-speech & audio analysis Speech-to-Text: Transcribe audio Text-to-Speech: Generate natural speech Audio Classification: Classify sounds Voice Activity Detection: Detect speech Speaker Diarization: Identify speakers Music Generation: Create music

The Howlers

YouTube Transcript Extractor

bulletproof/youtube-transcript-extractor

🎬 Convert any YouTube video to text. Extract transcripts, subtitles, and captions from videos, Shorts, and live streams. Get timestamped segments or full text in JSON, SRT, or plain text. Auto-captions speech-to-text fallback. 14+ languages. No login needed.