Hi @olive stratus. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
#PLS HELP
solar wraithBOT
You're in the right place to ask about OpenAI's voice generation! OpenAI offers free options for generating AI voices:
-
ChatGPT with voice: Available for free to all users via the ChatGPT mobile app. Just download the app and tap the headphones icon to start a conversation with AI-generated voice. This is a simple way to try out AI voice for free, though it's not a downloadable TTS API, but rather an interactive feature in the app ChatGPT with voice is available to all users.
-
OpenAI Text-to-Speech (TTS) API: OpenAI provides a TTS API that can generate lifelike speech from text. You can use the Audio API with the
gpt-4o-mini-ttsmodel, which supports free trial credits for new users. After the free credits, usage is pay-as-you-go, but you can experiment for free initially. Here’s a simple example in Python:from openai import OpenAI client = OpenAI() speech_file_path = "speech.mp3" with client.audio.speech.with_streaming_response.create( model="gpt-4o-mini-tts", voice="coral", input="Today is a wonderful day to build something people love!", instructions="Speak in a cheerful and positive tone.", ) as response: response.stream_to_file(speech_file_path) -
OpenAI.fm: You can try out the latest TTS voices interactively for free at OpenAI.fm (no code required).
Note: While OpenAI offers free trial credits, continued API use may require payment after those credits are used up. The ChatGPT app’s voice feature, however, is free for all users.