Questions tagged [speech-to-text]
Automatically converting recordings of speech into text
14
questions with no upvoted or accepted answers
8
votes
2
answers
13k
views
How do I to use Google Speech to Text in any Windows application?
When using Android, using the Swiftkey keyboard, I can use the Google Speech to Text anywhere, simply quickly holding a key. In my Windows PC, I want speak with the microphone and let Google type for ...
- 3,865
1
vote
0
answers
238
views
Speaker diarization with Node js using openai
I am developing whisper transcription in the node js using openai API. I am able to get the transcriptions for chunked files using ffmpeg library. I am struggling at the point of speaker diarization ...
- 111
1
vote
2
answers
499
views
How can you speed play mp4 files in chrome?
I was looking for ways for auto-generate subtitles for mp4 files and I ran across chrome's experimental features of live captioning. However I also want to play the mp4 file at 1.5x speed. How can I ...
- 111
1
vote
0
answers
1k
views
Google voice speech recognition,beep(music) file location in android for rooted device
I am working on speech recognization where I am continuously listening to user input.I have made a loop through which it listens continuously.
Whenever Recognizer starts to listen it will play an ...
- 61
0
votes
0
answers
50
views
Add Transcript to Audacity Track
I use Audacity for post-production of a podcast. It would be nice to have a transcription below the audio tracks, so it's easier to navigate.
Is there a way to automatically transcribe a track and add ...
- 3,247
0
votes
0
answers
37
views
Add timestamps to output? pocketsphinx
Been using pocketsphinx to successfully grab transcripts from wav files, and it made sense to me that there would be an argument for adding timestamps. Actually, there are SO MANY arguments in the ...
- 1,233
0
votes
0
answers
677
views
Windows 11 voice typing commands not working
So I recently discovered the Windows 11 voice typing feature (Win + H) and started using it. Allegedly it supports commands like "correct word" or "select word, but it doesn't work for ...
- 298
0
votes
2
answers
801
views
Speaker diarization for 3+ speakers using Azure
Does Azure's batch transcription support speaker diarization for more than 2 speakers?
I checked their Rest API documentation and didn't find anything relevant.
Are there other ways to do this using ...
0
votes
1
answer
1k
views
How to convert video to transcript locally on PC?
I am seeking a certain feature. At my University, the professor is recording his lectures, and uploading the videos to his website. On the website, he has some kind of software which converts his ...
- 223
0
votes
1
answer
863
views
How to make a bulleted list with speech recognition?
I'm trying to outline my textbook using a speech recognition tool (windows speech recognition, google's voice typing, or any other free software).
I haven't quite been able to get full outline ...
- 111
0
votes
1
answer
170
views
Impossible to select items DragonBar of Dragon NaturallySpeaking
When I open Dragon NaturallySpeaking 11, I can't select the items in the DragonBar. For example I click on Tools and the items like Transcribe Recording do not work. Could you help me?
- 1,102
0
votes
0
answers
1k
views
Enable English speech recognition on non-english Windows 7 Home Premium
It seems that non only that Microsoft didn't achieve to create speech recognition for any minor anguage, but they also intentionaly removed option to control your PC with English commands.
So is there ...
- 4,504
0
votes
1
answer
66
views
How to create a written transcript of a BBC radio broadcast where the media player does not provide Closed Captioning?
Am not entirely sure that this is the site to ask this question. If it is not, kindly migrate the question to the appropriate SE site.
On June 15, 2018 BBC World Service Weekend aired a program that ...
- 111
-1
votes
1
answer
2k
views
Converting .MOV audio files to Text
I have couple of audio files in the .mov format. Is there any software available which can convert the speech/lecture/conversation in that audio file into text?
- 99