@dark sparrow is it possible to enable voice in the assistants API?
#Voice in Assistants API
hasty zinc
dark sparrowBOT
Hi @hasty zinc. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
Hmm, I don't know enough to give you a confident answer yet. The provided extracts do not mention the capability to enable voice in the Assistants API. However, you can learn more about the capabilities of the Assistants API in the OpenAI documentation (https://platform.openai.com/docs/assistants).
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
hasty zinc
@dark sparrow what's with text to speach?
dark sparrowBOT
Let me check the knowledge base for you. One moment! :books:
OpenAI offers a Text-to-Speech (TTS) API that allows developers to generate high-quality spoken audio from text. It offers six preset voices and two model variants, tts-1 and tts-1-hd. The tts-1 model is optimized for real-time use cases, while tts-1-hd is optimized for quality. The pricing starts at $0.015 per 1,000 input characters (not tokens).
You can access the TTS API through the audio/speech endpoint if you have an OpenAI API account. The rate limits for the TTS API begin at 50 RPM for paid accounts. The maximum input size you can submit per request is 4096 characters, which is equivalent to approximately 5 minutes of audio at default speed. It's also possible to stream audio by setting stream=True, which allows you to chunk the returned audio file.