Emmy-Award winning Respeecher join us to share the future of synthesised speech.
Supporting Ukraine
The VoiceLunch Foundation is taking donations to help support the voice lunch and voice technology community in Ukraine. VUX World has, of course, donated. I plead with you to donate too.
Presented by Deepgram and Symbl.ai
Deepgram is a Speech Company whose goal is to have every voice heard and understood. We have revolutionized speech-to-text (STT) with an End-to-End Deep Learning platform. This AI architectural advantage means you don’t have to compromise on speed, accuracy, scalability, or cost to build the next big idea in voice. Our easy-to-use SDKs and APIs allow developers to quickly test and embed our STT solution into their voice products. For more information, visit:
See how easy it is to add simple but powerful call coaching and call tracking functionality to your customer experience solutions with Symbl.ai’s customizable Conversation Intelligence APIs. From calls to videos to text conversations — apply best in class contextual AI in no time by getting started for free.
Speech-to-speech
Emmy Award-winning Respeecher is changing the speech synthesis game. Move over TTS and SSML, and enter Speech to Speech.
From voice preservation, to accessibility, to voiceovers to film studios, the uses for speech to speech are endless.
Rather than programming machines to read text out loud, like most speech synthesis systems (text-to-speech), Respeecher uses it deep learning to sonically reproduce voices at film studio levels of fidelity. With Respeecher, a voice actor (or anyone) can simply speak and have their voice transformed into synthesised speech in next to real time. It reproduces all of the character and delivery in the voice, so that the resulting synthesised speech is exactly like the original source. Whether you shout, whisper or sing, the speech to speech technology will replicate everything. It’s truly ground breaking and has to be hear to be believed.
And you can hear it in the intro, as I introduce the episode using four different Respeecher voices.
Respeecher CEO, Alex Serdiuk, joins us to share more.
Timestamps
00:00 Intro and presenting Deepgram and Symbl.ai
04:05 Welcome Alex and closing the Ukraine airspace
08:40 About Respeecher
12:40 Sourcing voices
14:10 Nixon and winning an Emmy
17:37 Process of creating speech to speech
25:34 Limitations of TTS for long for audio
29:00 The future of voice acting
34:25 Voice marketplace
38:00 Pricing of speech to speech voices
42:00 How to achieve higher quality voices
43:30 Accessibility
48:50 Endless use cases
51:00 Ethics
55:54 Outro and more information
Links
Learn more at https://respeecher.com
