Aisha AI
by voicelab

Aisha API documentation

REST APIs for Uzbek speech - text-to-speech, speech-to-text and voice agents. Authenticate with an API key and make your first call in minutes.

Get API key Contact team Base URL https://back.aisha.group

For developers

Quickstart with cURL #

HTTP API

Set AISHA_API_KEY in your server environment and call the API directly from the server. Do not put the key in browser code.

TTS cURL request

curl --request POST \
  --url https://back.aisha.group/api/v1/tts/post/ \
  --header "X-Api-Key: $AISHA_API_KEY" \
  --header 'Accept-Language: uz' \
  --form 'transcript=Assalomu alaykum, bu AIsha TTS sinovi.' \
  --form 'language=uz' \
  --form 'model=Gulnoza' \
  --form 'mood=Neutral' \
  --form 'speed=1.0'
llms-api.txt

TTS API #

API v1 TTS Sync / Async Realtime

Text-to-Speech endpoints. For server-to-server integrations, send X-Api-Key with every request.

  • Send transcript to POST /api/v1/tts/post/ to generate audio.
  • Pass webhook_notification_url to run the request asynchronously and receive 202 Accepted.
  • Check the result through GET /api/v1/tts/status/{id}/ or history.
  • Use wss://back.aisha.group/api/v1/tts/realtime for realtime TTS over WebSocket or back.aisha.group:443 over gRPC.
  • Send multiple text turns over one persistent connection; do not reconnect for every turn.
  • TTS character billing is enforced after balance verification when the stream starts.

Endpoints

  • POST /api/v1/tts/post/ Generate audio
  • GET /api/v1/tts/status/{id}/ Check status
  • GET /api/v1/tts/get/?page=1&limit=10 History list
Open reference

STT API #

API v1 API v2 Realtime STT

Speech-to-Text endpoints. For server-to-server integrations, send X-Api-Key with each request.

  • POST /api/v1/stt/post/ for short audio (sync).
  • POST /api/v2/stt/post/ for long audio (async, returns task_id).
  • Use WebSocket wss://back.aisha.group/api/v1/stt/realtime for realtime audio.
  • Use gRPC endpoint back.aisha.group:443 for server streaming integrations.

Endpoints

  • POST /api/v1/stt/post/ Short-audio transcription
  • GET /api/v1/stt/get/?page=1&limit=10 v1 history list
  • POST /api/v2/stt/post/ Long-audio transcription (async)
  • WS /api/v1/stt/realtime?format=webm&token=YOUR_API_KEY Realtime WebSocket transcription
Open reference

Quick start #

  1. 1. Create an API key

    Generate an API key in Space and send it in the X-Api-Key header for every request.

  2. 2. Send a test request

    Validate the TTS/STT endpoints through cURL or backend code and confirm the response shape you expect.

  3. 3. Wire status and history

    For async flows, implement status and history to cover the full workflow.

Use X-Api-Key for server-to-server traffic. For large files and async tasks, implement history and status endpoints as part of the integration.

Machine-readable docs

A plain-text version of these docs is available for AI agents and LLMs.

For AI agents llms-api.txt