Skip to main content
kombify AI includes voice capabilities for speech-to-text (STT), text-to-speech (TTS), and voice chat.
Voice features require the voice module to be enabled. Check availability via GET /v1/ai/voice/health.

​
Voice chat

​
Voice chat (sync)

​
/v1/ai/voice/chat
Send text input and receive both text and audio response.

​
Voice chat (stream)

​
/v1/ai/voice/stream
SSE streaming endpoint for real-time voice chat.

​
Speech-to-text

​
Transcribe

​
/v1/ai/voice/transcribe
Transcribe audio to text. Accepts audio file upload.
curl -X POST https://api.kombify.io/v1/ai/voice/transcribe \
  -H "Authorization: Bearer $TOKEN" \
  -F "audio=@recording.wav"

​
Text-to-speech

​
Synthesize

​
/v1/ai/voice/synthesize
Convert text to speech audio.
curl -X POST https://api.kombify.io/v1/ai/voice/synthesize \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello, welcome to kombify", "voice": "alloy"}' \
  --output speech.mp3

​
Synthesize (stream)

​
/v1/ai/voice/synthesize/stream
Streaming TTS — audio chunks are sent as they are generated.

​
List voices

​
/v1/ai/voice/voices
List available TTS voices with their properties.

​
Speaker verification

Speaker verification requires the verifier module. Not available on all plans.

​
Enroll

​
/v1/ai/voice/enroll
Enroll a speaker voice profile for verification.

​
Verify

​
/v1/ai/voice/verify
Verify a speaker against an enrolled profile.

​
Health checks

EndpointDescription
GET /v1/ai/voice/healthOverall voice module health
GET /v1/ai/voice/tts/healthTTS subsystem health
GET /v1/ai/voice/stt/healthSTT subsystem health