Speech Services

Showing 12

Add Turkish to Speech-to-Text and Text-to-Speech services

According to Wikipedia Turkish is the 13th most spoken language in the world. It'd be very helpful to add Turkish to the Speech services since it is also often required in some client engagements!

almost 2 years ago in Speech Services 4 Not under consideration

18 VOTE

Ability to move fully trained STT models between separate instances (i.e. DEV vs. PROD or separate accounts)

Customers for best practice reasons keep environments separate (DEV vs. PROD) for security, performance, testing & availability of the model. Training STT models can take hours to train. Not utilizing fully trained models results in delays in...

about 6 years ago in Speech Services 4 Not under consideration

9 VOTE

Improve API response structure for timestamps and word_confidence within STT SpeechRecognitionAlternative model

As part of the response from making a POST to the v1/recognize endpoint in the Speech to Text service, the user receives an array of "alternatives". Within these "alternatives" objects, there are two arrays called "word_confidence" and "transcript...

almost 7 years ago in Speech Services 0 Not under consideration

2 VOTE

More language options for speech to text (Turkish)

I just enrolled for Speec to text API. Unfortunately the languages are limited to 13. I am wondering if IBM are planning to add more languages whereas Google supports 60. Turkish is one of the languages i would like to see.

almost 2 years ago in Speech Services 1 Not under consideration

4 VOTE

Add m4a speech to text support

This is a great format for content creation apps in iOS, why not support it?I have to get around by converting to wav or mp3 adding more waiting time

over 5 years ago in Speech Services 1 Not under consideration

1 VOTE

Watson Speech to Text should return timestamps accurate to milliseconds for transcription

Real-life scenario: Researchers from Brandeis University, Boston University, Harvard, Boston College, and Northeastern University are investigating cognitive aging and biomarkers of dementia. Currently, they have been hand-scoring cognitive interv...

almost 3 years ago in Speech Services 2 Not under consideration

2 VOTE

Automatic Voice Model detection

Automatically detect the voice model to improve transcription in use cases where multiple speakers have different accents (e.g. US and UK on the same line) - similar to language detection in Watson Assistant.

over 6 years ago in Speech Services 1 Not under consideration

1 VOTE

usability of the new IBM Watson tts demo site

When we did the project "spaceships with opinions" the IBM Watson tts-demo site was a great help. So I feel I have a responsibility to tell you how I think the new site is failing. https://www.ibm.com/demos/live/tts-demo/self-service/home It works...

almost 4 years ago in Speech Services 3 Not under consideration

1 VOTE

Retreive sound file previously streamed to Watson Speech-to-Text

When working on improving our product, we'd like to capture field failures that could be used to train our custom speech-to-text model. We have a wake word (handled locally) and then we establish a connection to IBM Watson's Speech-to-Text service...

almost 5 years ago in Speech Services 2 Not under consideration

1 VOTE

modification request for UI of the AI Minute asset

See attached document.

about 5 years ago in Speech Services 1 Not under consideration

Please enter your email address

FILTER BY CATEGORY