Compare Models
-
Microsoft
VALL-E
OTHERVALL-E is a LLM for text to speech synthesis (TTS) developed by Microsoft (technically it is a neural codec language model). Its creators state that VALL-E could be used for high-quality text-to-speech applications, speech editing where a recording of a person could be edited and changed from a text transcript (making them say something they originally didn’t), and audio content creation when combined with other generative AI models. Studies indicate that VALL-E notably surpasses the leading zero-shot TTS system regarding speech authenticity and resemblance to the speaker. Furthermore, it has been observed that VALL-E is capable of retaining the emotional expression and ambient acoustics of the speaker within the synthesized output. Unfortunately, VALL-E is not available for any form of public consumption at this time. At the time of writing, VALL-E is a research project, and there is no customer onboarding queue or waitlist (but you can apply to be part of the first testers group). -
LMSYS Org
Vicuna-13B
FREEVicuna-13B is an open-source chatbot developed by a team of researchers from UC Berkeley, CMU, Stanford, MBZUAI, and UC San Diego. The chatbot was trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. There is a 13B and 7B parameter models that are available on Hugging Face.
Vicuna-13B achieves more than 90% quality of OpenAI ChatGPT and Google Bard while outperforming other models like LLaMA and Stanford Alpaca in more than 90% of cases. The code and weights and an online demo are publicly available for non-commercial use. Here is a link to learn more about how it compares to other models – https://lmsys.org/blog/2023-03-30-vicuna/.
To use this model, you need to install LLaMA weights first and convert them into Hugging Face weights, and the cost of training Vicuna-13B is around $300.
-
OpenAI
Whisper
0.006Whisper is an automatic speech recognition (ASR) system capable of transcribing in multiple languages as well as translating them into English. With Whisper, you can easily transcribe speech into text, allowing you to capture conversations and meetings for future reference. And if you need to communicate with someone who speaks a different language, Whisper can help with that too — it can translate many different languages into English, making it easier than ever to bridge the gap and ensure that everyone is on the same page.
Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification. The speech to text API has two endpoints (transcriptions and translations) and file uploads are currently limited to 25 MB, and the following input file types are supported: mp3, mp4, mpeg, mpga, m4a, wav, and webm.
