Duhi Voice

Paste a script, choose a voice, and get an MP3. Long texts run in the background, so you can leave this page and come back.

0 characters Open .txt file

Your recordings

Files are kept for a limited time, so download what you need.
Save your API key to see your recordings.
Use the API

Long text: create a job, check it until status is done, then download audio_url.

curl -X POST ORIGIN/v1/jobs \
  -H "Authorization: Bearer YOUR_KEY" -H "Content-Type: application/json" \
  -d '{"text":"Hello world","voice":"en-US-AvaMultilingualNeural","rate":"+0%"}'

curl ORIGIN/v1/jobs/JOB_ID -H "Authorization: Bearer YOUR_KEY"

Short text (OpenAI-compatible, returns the MP3 directly):

curl -X POST ORIGIN/v1/audio/speech \
  -H "Authorization: Bearer YOUR_KEY" -H "Content-Type: application/json" \
  -d '{"model":"tts-1","input":"Hello world","voice":"alloy","speed":1.0}' -o hello.mp3

All voices: /v1/voices (filter with ?locale=en-US).