Skip to main content

Kitsch Labs API

Kitsch Labs API is a developer API that converts text into natural, expressive speech. It provides Text to Speech with ready-to-use voices, single-request Voice Cloning that accepts reference audio directly in the request, Noise Reduction, and file or realtime Speech to Text.

What can I do with the API?​

  • List available voices
  • Synthesize text as MP3 or WAV audio
  • Clone a voice by attaching reference audio to a single request
  • Reduce continuous background noise in an audio file
  • Transcribe audio files or realtime audio streams

How do I get started?​

All API requests use the following Base URL and the xi-api-key header.

Base URL: https://api.kitschlabs.com
Header: xi-api-key: <API_KEY>
List available voices
curl "https://api.kitschlabs.com/v1/voices" \
  --header "xi-api-key: <API_KEY>"

Get started with the Text to Speech API

For single-request synthesis with reference audio, see the Voice Cloning API. To process background noise, see the Noise Reduction API. To transcribe audio, see the Speech to Text API.

Keep API keys on the server

Do not put API keys in browsers, mobile app bundles, or public repositories. Store them in server environment variables or a secret management service.

Kitsch LabsProducts and companyServiceSign in and use Kitsch Labs servicesPricingPublic plans and usage terms

Need help?​

For account, API key, billing, or technical questions, email giopaik@kitschlabs.com. Include the x-kitsch-request-id response header when reporting an error to help us investigate it faster.