Загрузка видео...
Не удалось загрузить видео
🚨 BREAKING: Text to Speech is coming to Runway “Text to Speech allows you to generate voice overs and dialogue in a number of different voices, all within Runway.” It’s now available to all CPP members. Here’s a quick preview including sample audio I generated, featuring a quote from... show more
27,262 просмотров • 2 лет назад •via X (Twitter)
Комментарии: 11
@TinfoilTricorn @runwayml These are Elevenlabs voices 100%
@runwayml Excellent always good to have everything in the one place
@Ishouldtrythat1 @runwayml Yes a one stop shop for creative storytelling and video production
@runwayml Nice, but a bit robotic, I hope they improve it quickly
@runwayml Yeah just getting started but I rushed a recording before rushing out the door Some sounded more natural @iamneubert was doing some cool multi-lingual experimentations I didn’t even see this coming so I’m now psyched for their audio roadmap
@runwayml Where’d you hear this? Are they talking about it at the conference?
@runwayml They announced it in their private Discord channel for Creative Partners Program (CPP) members
@runwayml Any word if this is their own speech model (ie, not ElevenLabs?) Also curious if they will offer this via API?
@runwayml I’ve seen no mention of partnership with ElevenLabs and it appears to be their own homegrown audio tool They already had some other audio tools
@runwayml I like the direction this technology is headed. Makes the workflow more efficient. (Prediction - Wav2Lip integration coming next)
@runwayml Totally been thinking the same thing 🤝 Runway is a one stop shop for generative storytelling
![Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.](https://image.24vids.com/tw-1672048076469698561/ext_tw_video_thumb/1672047839378300928/pu/img/MuoOBsAyUd-HAI7D.jpg)
