How to convert text to speech with an API

Generate spoken audio from text with a TTS model.

Call the speech endpoint

Send text and a voice to the audio speech endpoint and save the returned audio file.

Example

from openai import OpenAI

client = OpenAI(api_key="YOUR_TOKENREX_KEY", base_url="https://tokenrex.ai/api/public")
audio = client.audio.speech.create(model="gpt-4o-mini-tts", voice="alloy", input="Hello from TokenRex")
audio.write_to_file("hello.mp3")

Get API key Cost calculator Docs

Questions

Do I need a separate key for each provider?: No. One TokenRex API key works for every enabled model; change only the model ID.

Related