Silkwave Voice
Silkwave Voice is a privacy-focused audio recording and transcription app for macOS. Record from your microphone, system audio, or both at once - with accurate, real-time transcription powered by Apple's on-device speech-to-text models. No cloud uploads, no subscriptions, no per-minute API costs.
RECORD ANY AUDIO SOURCE
• Microphone - voice notes, in-person meetings, dictation
• System Audio - Zoom, Google Meet, Teams, YouTube, browser tabs
• Both at once - capture your mic and remote participants simultaneously
ON-DEVICE TRANSCRIPTION
• Real-time speech-to-text using Apple's on-device models
• 10 languages: Cantonese, Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Spanish
• Completely local - no internet connection needed
AI-POWERED SUMMARIES
• Structured summaries with key topics, action items, and decisions
• Powered by ChatGPT through Apple Intelligence - no API keys needed
Learn more about Silkwave Voice
TranscriptFetch
TranscriptFetch turns YouTube, TikTok, Instagram videos and podcasts (Spotify, Apple, or any RSS feed) into clean, structured transcripts your app, RAG pipeline, or AI agent can read and cite. Returns plain text or per-segment timestamps as JSON.
Videos without a caption track are transcribed automatically, so you get a result whether or not captions exist. YouTube also resolves channels, playlists, and keyword searches into video lists, and a batch endpoint fetches up to 50 transcripts in one call.
Learn more about TranscriptFetch
Subanana
Subanana is an AI speech-to-text web app that turns audio and video into subtitles, transcripts, and meeting summaries in 80+ languages, with standout accuracy on Asian and mixed-language speech (Cantonese, Mandarin, Japanese, Korean, and code-switching) that English-first tools handle poorly.
Subtitles: import a file or a YouTube/Instagram/Facebook link, edit with a glossary and AI auto-correct, and export SRT, VTT, TXT, DOCX, bilingual subtitles, or burned-in video.
Transcripts: speaker labels, filler-word removal, automatic punctuation and paragraphs.
Meeting summaries: templates, decisions and action items, plus a Google Meet and Microsoft Teams recording bot that processes the meeting after it ends.
Live captions: real-time captioning with translation for events.
Learn more about Subanana
Transcriptik
Transcriptik turns audio and video into text. Paste a TikTok, Instagram or YouTube link, use a direct media URL, or upload a file to generate a transcript in 99+ languages with timestamps and speaker labels. A free plan is available. Paid plans add transcript editing and exports in TXT, PDF, DOCX, SRT and VTT. Pro and Studio plans also include AI summaries, rewriting, content repurposing and translation.
Learn more about Transcriptik
