aisplice

By capability

Speech & transcription

No model serves this yet

Nothing in the model catalogue supports this route right now. The page stays for reference.

#Text to speech

/v1/audio/speech returns raw audio bytes — save the response body straight to a file. voice and response_format follow the OpenAI TTS parameters.

tts.sh
curl https://www.aisplice.store/v1/audio/speech \
  -H "Authorization: Bearer $KEY" -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "voice": "alloy",
    "input": "Hello from the gateway."
  }' --output hello.mp3

#Transcription

/v1/audio/transcriptions is multipart: upload the audio file plus the model name. /v1/audio/translations uses the same shape and returns English.

transcribe.sh
curl https://www.aisplice.store/v1/audio/transcriptions \
  -H "Authorization: Bearer $KEY" \
  -F file=@meeting.mp3 \
  -F model=whisper-1

# → {"text": "…transcript…"}

Every field: /v1/audio in the API reference →

Still stuck?

Send us the request ID or the error message and we will look into it.

Previous3D modelsNextUpload files