- Step 1: Enter a name for your audio file.
- Step 2: Select from one of six AI voices.
- Step 3: Paste in your OpenAI API key.
- Step 4: Paste in your text from the source.
- Step 5: Click the "Run" button.
- Step 6: Wait while we generate your audio file.
- Step 7: Click the link to download your audio file.
SpeakEasy
Text-to-Speech for Everyone
- Do I need an account? SpeakEasy works on an ad hoc basis. No accounts. No subscriptions. Just fast, quality audio when you need it.
- How much does it cost? SpeakEasy is free to use. However, OpenAI will charge you for the audio generation. Each file usually costs a few cents to create.
- What happens to my API key and audio file? We never store your keys or files. When you leave SpeakEasy they do too.
- What do I do if I don't have an API key? You can get one by following these instructions.
- How do I know which AI voice to use? You can listen to samples of each voice here.
- How much text can I convert to audio? We currently support around 5000 words or about 30 minutes of audio.
- What model does this use? We use the OpenAI tts-1-hd model. This model takes a bit longer to run, but the output quality is worth the wait.
- I clicked "Run", is this thing actually working? Yes. Depending on the amount of text, processing can take anywhere from a few seconds to a few minutes.
- What is the quality of the output? You can listen to some sample outputs here.
- Can I build my own? Sure, you can find the code on GitHub.