API reference
Every endpoint, with links to the page that documents it.
Every endpoint, with links to the page that documents it in full. The live OpenAPI spec is at https://api.kenpathlabs.com/openapi.json.
Speech
/v1/audio/speechPrimary TTS: text in, audio out; set stream for a chunked response. Every response carries an x-request-id — send your own and it is echoed back. See Text to speech.
/v1/text-to-speech/{voice_id}/v1/text-to-speech/{voice_id}/stream/v1/text-to-speech/{voice_id}/with-timestamps/v1/text-to-speech/{voice_id}/stream/with-timestampsElevenLabs-compatible synthesis, incl. streaming and character timestamps (one JSON object, or newline-delimited objects when streamed; timings are word-accurate, character-approximate). output_format like mp3_44100_128, pcm_24000. See SDKs.
WebSocket
/v1/audio/speech/stream-inputNative input streaming with mode=eager. Send text fragments, receive PCM. See Input streaming.
/v1/text-to-speech/{voice_id}/stream-inputElevenLabs-compatible realtime WebSocket (BOS/text/flush/EOS protocol).
Voices
/v1/voices/v1/voices/{voice_id}/v1/voices/{voice_id}/previewRoster, single voice, and bundled preview clip. No auth.
/v2/voicesSearch and paging over the same 320-voice roster (the ElevenLabs SDK’s voices.search()): search matches every word against id, name, accent, gender, description and labels; page_size (1–100), next_page_token, category. Needs a key.
/v1/voices/{voice_id}/settingsStub for ElevenLabs SDK compatibility: returns permissive defaults so client flows that read voice settings don’t break.
Utility
/healthLiveness: {"status": "healthy"}. No auth.
/v1/languages/v1/modelsSupported languages, and the one model: svara-tts-turbo. No auth.
/v1/pronunciation-dictionaries/v1/pronunciation-dictionaries/{id}/v1/pronunciation-dictionaries/add-from-rulesList, read and create pronunciation dictionaries with your API key. Creation is all-or-nothing; deletion is in the console.
/v1/usage/v1/user/subscriptionYour plan, balance and month-to-date usage — the second is the ElevenLabs-shaped dialect. See Usage & subscription.