#how can i get the new tts model being a research project?

1 messages · Page 1 of 1 (latest)

hidden minnow
#

how can i get the new tts model of gpt4o in the API? i need to talk with somebody, its an research project

frigid willowBOT
#

Hi @hidden minnow. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

#

To access the new Text-to-Speech (TTS) model, you need to have an OpenAI API account. The TTS model is available via the Speech endpoint in the Audio API. OpenAI offers two different model variates, tts-1 optimized for real-time text-to-speech use cases, and tts-1-hd optimized for quality [source (https://platform.openai.com/docs/models)].

However, please note that as of the latest updates, the gpt-4o model currently supports text and vision modalities, and the support for audio is planned to be added in the future [source (https://community.openai.com/t/744549), source (https://community.openai.com/t/744455)].

If you are a research project and need to discuss further, you might want to reach out to OpenAI directly through their official communication channels.

Also, ensure that your project settings allow the use of the desired models. If not, you might need to add them to the list of allowed models [source (https://community.openai.com/t/745038)].

For more information on how to use the models, you can refer to the OpenAI documentation and the OpenAI Playground [source (https://help.openai.com/en/articles/7102672-how-can-i-access-gpt-4-gpt-4-turbo-and-gpt-4o#h_9bddcd317c), source (https://community.openai.com/t/599553)].

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:

#

@hidden minnow kapa.ai is still learning and improving, please let us know how it did by reacting below