**Now on the App Store 🎙️**

Turn your voice into text in seconds with SpeechWave.

✓ Real-time transcription
✓ 50+ languages
✓ Edit before saving
✓ Keep your recordings and transcripts organized

Whether you're capturing ideas, meetings, notes, or voice memos, SpeechWave helps you get words on screen fast.

Download SpeechWave on the App Store today.

#SpeechWave #VoiceToText #Transcription #Productivity #iPhoneApps #AppStore #NotesApp #VoiceNotes #SpeechRecognition #iOSApps

Because we are embedded in tech monopolies, something like three companies' products need to add those words in order for them to end up in documents. #Microsoft and #Apple are now de-facto the Acadamie Anglais. Not people determining language, but companies imposing it.

#language #linguistics #gonna #wanna #VoiceToText #spellcheckers #technology

But I don't think that's exactly what's going on, here. I think voice-to-text and spellcheckers added those words, and probably many others, and we're all just kind of going with it.

#language #linguistics #gonna #wanna #VoiceToText #spellcheckers #technology

I have noticed a lot of official sources uses "gonna" and "wanna" in writing. This has been happening for a while.

So look, language evolves. Words come into existence when speakers of a language choose to use them, and people have been saying "gonna" and "wanna" for at least many decades, possibly centuries.

#language #linguistics #gonna #wanna #VoiceToText #spellcheckers #technology

@v_d_richards ich nutze vibe.

Läuft lokal. Ist noch verbesserungsfähig, kann aber schon ganz gut mehrsprachig.

https://thewh1teagle.github.io/vibe/

Edit: Tippfehler im Link behoben

#vibe #linux #voicetotext #transcription #Audiotranskription #videotranskription #SpracheZuText #spracherkennung #spracherkennungsprogramm #Spracherkennungssoftware

Vibe - Local Audio & Video Transcription App

Local-first transcription for audio and video with AI summaries, multilingual support, and privacy-focused processing.

Vibe

𝗛𝗮𝗻𝗱𝘆 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿:

#VoiceToText #OpenSource

https://thewhale.cc/posts/handy-computer

Speak into any text field, the free and open source app for speech to text.

Локальный голосовой ввод: Whisper + Ollama на Python

Мне нужен был голосовой ввод. Не диктовка в Google Docs, не облачный API — а простая штука: зажал клавишу, сказал, отпустил, текст появился в активном окне. Локально, без отправки аудио куда-либо. Готовых решений, которые бы устроили, сходу не нашёл. Сделал свое. Может, кому будет полезно.

https://habr.com/ru/articles/1009538/

#whisper #ollama #speechtotext #voicetotext #pushtotalk #голосовой_ввод #python #localfirst #privacy

Локальный голосовой ввод: Whisper + Ollama на Python

Мне нужен был голосовой ввод. Не встроенная в ОС диктовка, не облачный API — а простая и главное локальная...

Хабр

People have been raving to me about how good voice-to-text has become, so I'm trying Wispr Flow. But the user experience feels a bit off: I have to stop recording to get it to type out the text? Not really "hands-free", is it?
Is that just how it works, or is there a continuous dictation mode I'm missing? Are there other LLM-based tools that behave more like classic dictation?
Looking forward to your recommendations!

#VoiceToText #AI #Productivity

SoundVibes 0.2.0 is out!

- More people than me that needed to handle multiple languages without the delay of the autodetection.
- Now possible to toggle specific languages to transcribe.

Still modest amount of users, but ⭐ are rising as well as downloads.

#voicetotext made easy on #linux!

https://github.com/kejne/soundvibes/releases/tag/v0.2.0

Release v0.2.0 · kejne/soundvibes

Breaking changes The model & language loading has been given an overhaul, separating the model loading in the daemon with the language triggering by the client Check the docs for the updated conf...

GitHub