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
Zeemo AI
Simply upload subtitle and video files to automatically match text to video content. Upload video and raw transcript file without timeline information. Timestamps will be automatically added to the transcriptions. Edit it online, then download subtitle files or video with subtitles directly. Original video language supports English, Spanish, Simplified Chinese, Traditional Chinese, Cantonese, Japanese, Korean, French, Thai, Russian, Portuguese, German, Italian, Vietnamese, Arabic. Single line word limit means the maximum number of words in a line of subtitles. When a paragraph contains many words, the system will make reasonable cuts according to the single line word limit to ensure that the number of words in a line of subtitles does not exceed the limit, therefore improving the subtitle display and facilitating reading.
Learn more about Zeemo AI
Speecho
Speecho is a browser-based, pay-as-you-go speech and language app for people working with recordings, live speech, and written content. It transcribes audio and video into timestamped text with speaker labels, and can produce summaries, translations, and SRT or VTT subtitles. For live sessions, it displays captions and translated subtitles through a shareable viewer page or an OBS browser overlay, with an optional spoken interpreter. Text-to-speech tools turn written material into downloadable MP3 audio, while other tools support dictation, burned-in video captions, handwriting recognition, and document scanning. Speecho runs in a web browser on computers and mobile devices, with prepaid credits rather than a recurring subscription. It serves people who need transcription, accessibility captions, translation, or voice-over output for podcasts, classes, meetings, streams, interviews, and other spoken or written material.
Learn more about Speecho
Trippi
Trippi adds live translated subtitles to Google Meet, Zoom (web) and Microsoft Teams (web). It captures the meeting audio and runs its own speech recognition and translation instead of re-translating the platform's own captions, so it also works where the platform offers no translation at all.
45 languages, in any direction. Dual subtitles show the original line and its translation together, or the translation alone. Captions are visible only to you — no bot joins the meeting, nothing is announced to other participants. The audio is never recorded or sold; the transcript stays in your own browser.
After the call: a full transcript, bilingual notes with who said what, and a summary with decisions, tasks and open questions. Free to start, no card, no Workspace admin.
Learn more about Trippi