Introduction - Mihu API Documentation

Ses turns text into speech and streams the audio while it is generated. Model: mihu-ses-v1. Audio is 24 kHz mono.

Authentication

Every request except /health needs Authorization: Bearer <KEY> (or ?api_key=<KEY>). A missing or wrong key answers 401.

Regions

Region	Base URL
Europe	`https://tts.eu.mihu.ai`
Türkiye	`https://tts.tr.mihu.ai`

Choose the region when you call the API: the two regions have the same paths, fields and answers, and your data stays on the server of the region you call. Examples use the Europe address. Every REST endpoint has a page under API Reference where you can pick the region, send a request and see the answer.

Quick start

curl -s https://tts.eu.mihu.ai/v1/audio/speech -H "Authorization: Bearer $KEY" -H 'Content-Type: application/json' \
  -d '{"model":"mihu-ses-v1","language":"tr","input":"Siparişiniz 28 Ekim günü saat 14.30da teslim edilecek.","response_format":"wav"}' \
  -o out.wav

curl -s https://tts.tr.mihu.ai/v1/audio/speech -H "Authorization: Bearer $KEY" -H 'Content-Type: application/json' \
  -d '{"model":"mihu-ses-v1","language":"tr","input":"Siparişiniz 28 Ekim günü saat 14.30da teslim edilecek.","response_format":"wav"}' \
  -o out.wav

Endpoints

Method	Path	Use
`POST`	`/v1/audio/speech`	Text to audio, streamed
`GET`	`/v1/voices`	Our voices and your custom voices
`POST`	`/v1/voices`	Create a custom voice from a recording
`GET`, `DELETE`	`/v1/voices/{id}`	One custom voice; delete it for good
`GET`	`/v1/models`	Model list
`GET`	`/health`	Service state and languages