Text-to-speech (TTS) for character voice output and speech-to-text (STT) for transcription. Both endpoints require a Bearer token.
Every route and HTTP method below was checked directly against the live ts-api source on August 13, 2026. Response bodies are illustrative examples, never captured responses.
Base URL
https://api.dyva.ai/v1/v1/voice/ttsSynthesize speech from text. Returns an audio/mpeg binary stream, or a JSON error body on failure (400/410/502/503).
Route and method verified directly against the live ts-api source on August 13, 2026.
Request body (3)
textstringRequiredvoice_idstringOptionaldyva_idstringOptionalExamples (3)
curl -X POST https://api.dyva.ai/v1/voice/tts \
-H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
-H "Content-Type: application/json" \
-d '{"text": "Hello from Dyva!", "dyva_id": "dyva_EXAMPLE0001"}' \
--output speech.mp3/v1/voice/sttTranscribe an audio file to text. Response has two fields: transcript and confidence. There is no detected-language field.
Route and method verified directly against the live ts-api source on August 13, 2026.
Request body (1)
audiofileRequiredResponse
Illustrative example, not a captured response{
"transcript": "Hello from Dyva!",
"confidence": 0.97
}Examples (3)
curl -X POST https://api.dyva.ai/v1/voice/stt \
-H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
-F "[email protected]"