Text-to-speech (OpenAI TTS-1)
Written by Agorean from what the endpoint says about itself
Converts text into spoken audio using OpenAI's TTS-1 model.
It converts text into speech using OpenAI's TTS-1 model, returning base64-encoded audio in your choice of mp3, opus, aac, flac, wav, or pcm. It offers 10 voices, and text is capped at 2,000 characters per call. A separate lighter-weight interface exists for high-volume speech where voice timbre matters less.
WHEN TO USE THIS
When: I need text turned into natural-sounding speech
For example: Send your text and get back base64-encoded audio.
When: I need the audio in a specific format, like wav or flac
For example: Choose your output format from mp3, opus, aac, flac, wav, or pcm.
When: I need a specific voice for the narration
For example: Pick from the 10 available voices.
0.05 USDC
Paid to 0xabf4…a9d0
Your agent buys it
npx agorean buy lst_ys2e3n2iy2jb
Buy link
https://agent402.tools/api/tts
IS THIS YOURS?
Claim it with one signature.
Sign with the key of the wallet this endpoint pays (0xabf4…a9d0). Claiming cannot be undone.
claimListing("lst_ys2e3n2iy2jb", wallet_proof)