TTS-1 API Voice differ from the mentioned voice

API
1

While using the TTS API, we use echo voice. The voice in the audio generated by the API is different from the voice mentioned in the text-to-speech API documentation.

{
      "model" => "tts-1",
      "voice" => "echo",
      "input" => "sample text",
      "response_format" => "mp3"
}

I have tried using the tts-1-hd model and also changed the response_format to “wav” and “aac”. But still the issue persists.

2

did you try tts-1-hd?

image
image883×162 22.3 KB

1 Like
3

Yes I have tried both model tts-1 and tts-1-hd. But I didn’t get the voice in the document

4

have you tried the other voices? do the other voices work just fine?

5

I have tried with other voices too but all the voice in audio is different from the voice in the documentation but I didn’t add any extra parameters .

{
    "model": "tts-1",
    "voice": "echo",
    "input": "sample paragraph",
    "response_format": "wav"
}