Just shipped a free Chrome extension - voice typing in 55+ languages. Click, dictate, auto-copies to clipboard. Paste anywhere.
No login needed.
Google approved it in 24 hours!
chromewebstore.google.com/detail/voice-to-text-voicetote/pdkdolmpbgnfnidpbijmhfdbehomokok
#buildinpublic #speechtotext
For the ones that use #murena #eos and miss #speechToText
Give #futo keyboard a try https://keyboard.futo.org/
Researchers 🔍
Turn interviews into insights faster with Transgate.
transgate.ai
#Transgate #SpeechToText #Research
![Overall architecture of AlphaFlowTSE. Given a mixture waveform y and an enrollment utterance e, we compute complex STFT features and form the mixture feature Y and enrollment feature E (real/imaginary concatenation). During training, the backbone takes the current state feature zt; during inference we initialize z0 = Y . The enrollment feature is concatenated as a temporal prefix, yielding [E∥zt] (or [E∥z0] at inference), which is fed to the UDiT backbone. The backbone is conditioned via AdaLN on the absolute time t and the interval length ∆ = r − t (with r = 1 at inference), and predicts the mean velocity for finite-interval transport, denoted uθ(t, r, [E∥zt]). One-step inference (NFE= 1) produces an estimated complex STFT Sˆ = (SˆRe, SˆIm), which is converted to the
target waveform sˆ by iSTFT. The dashed module is an optional mixing-ratio predictor used only in the background-to-target ablation to predict the start coordinate](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:gf4ewk42xvbpnrq3k2yapgqk/bafkreifnplebiv5xo5cehvlwymtxfew2udqxz54nnx2odypp3wl4z7q7vm)
Overall architecture of AlphaFlowTSE. Given a mixture waveform y and an enrollment utterance e, we compute complex STFT features and form the mixture feature Y and enrollment feature E (real/imaginary concatenation). During training, the backbone takes the current state feature zt; during inference we initialize z0 = Y . The enrollment feature is concatenated as a temporal prefix, yielding [E∥zt] (or [E∥z0] at inference), which is fed to the UDiT backbone. The backbone is conditioned via AdaLN on the absolute time t and the interval length ∆ = r − t (with r = 1 at inference), and predicts the mean velocity for finite-interval transport, denoted uθ(t, r, [E∥zt]). One-step inference (NFE= 1) produces an estimated complex STFT Sˆ = (SˆRe, SˆIm), which is converted to the target waveform sˆ by iSTFT. The dashed module is an optional mixing-ratio predictor used only in the background-to-target ablation to predict the start coordinate
Imagine a noisy group call where 3 people talk at once.
This paper builds a model that can focus on a single speaker (using a short voice sample) and extract that voice.
This cleanup results in better, faster audio transcription.
Summary and full paper 👇
#AudioML #SpeechToText
Screenshot from Google Docs, with spelling suggestion of the word deaf in place of the word death
Yes, I mean 'deaf', I always mean 'deaf', I am not talking about 'death' individuals or the 'death' community... #Google #VoiceTyping #SpeechToText #DeafNotDeath
Would anyone know of any good speech to text software/app that costs little to no money? Because the current ones I'm using are so useless that I have to end up typing to correct mistakes, which, on a bad day means I can't do anything anyways.
#disability #accessibilitytools #speechtotext #dystonia
🎤 Dictée vocale + IA
Comme pour d'autres tâches, l'IA vient renforcer l'efficacité de cette pratique en simplifiant le processus. ✍️
Murmure transcrit votre voix en texte, 100% hors ligne :
👉 www.it-connect.fr/murmure-dict...
#Murmure #IA #OpenSource #SpeechToText
Empty lecture hall with wooden seats, facing a chalkboard, featuring the text “The Top 75 Community College Titles” and a “CHOICE” logo.
This week on #LTIBlog
Our contributors from Ontario Council of University Libraries (OCUL) evaluate AI speech-to-text tools for access, discovery, and preservation. ow.ly/rLLv50Yl72V
#AI #Librarytech #speechtotext @ocul-libraries.bsky.social
Ideal for live subtitling and voice assistants! 🛠️⚡ #SpeechToText #TechNews #Mistral
I even setup satellite sites with just a simple landing page to drive traffic-
speechtotext.online
texttospeech.site
All forwarding traffic to voicetotextonline.com
#buildinpublic #speechtotext #voicetotext #texttospeech #STT #TTS #Productivity #Dictation #google
I developed VoiceToTextOnline dot com in a period of 3 months and now the site has started surfacing 200 users per day.
it ranks No.2 on Bing but its a far away story on Google.
#buildinpublic #speechtotext #voicetotext #texttospeech #STT #TTS #Productivity #Dictation #google
Free voice-to-text that actually works.
→ 55+ languages (Hindi, Spanish, Arabic, and more)
→ No signup required
→ Works right in your browser
→ Real-time transcription
Try it: voicetotextonline.com
#buildinpublic #speechtotext #voicetotext #texttospeech #STT #TTS #Productivity #Dictation
🎙️ تران스크ريبشن 60 دقيقة اجتماع كامل… مرة واحدة! 😱
VibeVoice-ASR (من Microsoft) نموذج 9B فقط مفتوح المصدر… بيعمللك حاجات النماذج الغالية مش بتعملها!
ليه VibeVoice كنز للمطورين وصناع المحتوى؟ 👇
#VibeVoice #ASR #SpeechToText #Diarization #OpenSourceAI #MicrosoftAI #حسام_الدين_حسن #خبير_اونلاين
ace549ad-9d03-445b-be42-f65578069df3
Most speech-to-text tools are privacy nightmares. Handy changes everything by keeping your voice on your computer.
It's open-source, free, and works with a simple keyboard shortcut. No cloud, no subscription, no nonsense.
Take your privacy back at handy.computer 🎙️
#SpeechToText #OpenSource
ace549ad-9d03-445b-be42-f65578069df3
Most speech-to-text tools are privacy nightmares. Handy changes everything by keeping your voice on your computer.
It's open-source, free, and works with a simple keyboard shortcut. No cloud, no subscription, no nonsense.
Take your privacy back at handy.computer 🎙️
#SpeechToText #OpenSource
github.com/chaosslab... is a #FastAPI wrapper that server an #OpenAI compatible server to run #SpeechToText transcriptions in a machine in your network so you can use #Whisper to transform your audios into text :D
https://github.com/silvabyte/Audetic
Looks interesting.
#Opensource #SpeechToText #VoiceCommands #Dictate
Whispr Flow together with Le Chat is a godsend. This works so nicely and dictation with Flow is really great in contrast to Apple's own onboard dictation feature
#ai #speechtotext #dictation #whisprflow #lechat
Letterly : L'apps pour dicter et rédiger par IA#IAGénérative #Productivité #dictéeIA #Letterly #productivitémobile #speechtotext #transcriptionintelligente
Letterly : L'apps pour dicter et rédiger par IA#IAGénérative #Productivité #dictéeIA #Letterly #productivitémobile #speechtotext #transcriptionintelligente
Overview: Hacker News explored "Handy," a free, open-source speech-to-text app. Users praise its speed, accuracy, and local processing, comparing it to paid options. The discussion also covered its potential integration with coding and LLMs. #SpeechToText 1/6
Academic success starts here 📚
Transcribe lectures and interviews easily with Transgate.
transgate.ai
#Transgate #SpeechToText #Students #Education #Translation #audiototext #Transcription #Transcribe
#TRANSKRIPTION #AUDIO #SPEECHTOTEXT #KI #EFFIZIENZ #CONTENTCREATION #ACCESSIBILITY #PODCASTING #DIGITALISIERUNG #UNTERTITEL #TRANSCRIPTION #AUDIO #SPEECHTOTEXT #AI #EFFICIENCY #CONTENTCREATION #ACCESSIBILITY #PODCASTING #DIGITALIZATION #SUBTITLES
✦ Scribe v2 : la transcription qui devient une brique produit. Et si tes sous-titres devenaient enfin un actif, pas une corvée ?
#KingLand #ElevenLabs #ScribeV2 #SpeechToText #Transcription #SousTitres #Audio #Podcast #IA #Productivité #Workflows
📌 Lire la fiche d’impact :…
www.wired.com/story/handy-...
Handy, a free Speech to text app that leverages AI, to make it simply dictate documents on your system. Simply hold Ctrl+Space while talking, and what you say will be transcribed onto the currently active text-box.
#Software #AI #Dictation #SpeechToText #Productivity
