# Aisha AI - API reference for AI agents

Aisha provides REST APIs for text-to-speech (TTS) and speech-to-text (STT).
This file summarizes the server-side HTTP integration. Human-readable reference:
https://aisha.group/en/api-documentation

## Base URL and authentication

- Base URL: `https://back.aisha.group`
- Send the API key in the `X-Api-Key` header for authenticated API requests.
- Keep the key on your server. Do not embed it in browser code or public examples.
- API keys are managed at https://voicelab.uz/app?utm_source=aisha
- API errors may be localized with `Accept-Language: uz`, `en`, or `ru`.

## Text-to-speech

### POST /api/v1/tts/post/

Converts text to audio. A request without `webhook_notification_url` runs
synchronously. See the human reference for request fields, response shapes,
status polling, and history.

```sh
curl --request POST \
  --url https://back.aisha.group/api/v1/tts/post/ \
  --header "X-Api-Key: $AISHA_API_KEY" \
  --header 'Accept-Language: en' \
  --form 'transcript=Salom dunyo' \
  --form 'language=uz' \
  --form 'model=Gulnoza' \
  --form 'mood=Neutral' \
  --form 'speed=1.0'
```

## Speech-to-text

### POST /api/v1/stt/post/

Uploads a short audio file for synchronous transcription. See the human reference
for supported fields, formats, and response details.

```sh
curl --request POST \
  --url https://back.aisha.group/api/v1/stt/post/ \
  --header "X-Api-Key: $AISHA_API_KEY" \
  --form 'audio=@./audio-file.mp3' \
  --form 'language=uz'
```

### POST /api/v2/stt/post/

Uploads audio for asynchronous transcription. Use the documented v2 detail
endpoint `GET /api/v2/stt/get/{id}/` to check the result. See the human
reference for request fields and response details.

## Links

- API overview: https://aisha.group/en/api-documentation
- TTS reference: https://aisha.group/en/api-documentation/text-to-speech
- STT reference: https://aisha.group/en/api-documentation/speech-to-text
- AI agents guide: https://aisha.group/en/ai
- General company context: https://aisha.group/llms.txt