Skip to content

OpenAiSpeech

PropertyPatternTypeDeprecatedDefinitionTitle/Description
+ implementationNoconstNo-Implementation
- text_to_speech_modelNoenum (of string)No-Text To Speech Model
- text_to_speech_voiceNoenum (of string)No-Text To Speech Voice
- speech_to_text_modelNoconstNo-Speech To Text Model
- speech_to_text_temperatureNonumberNo-Speech To Text Temperature

1. Property implementation

Title: Implementation

Typeconst
RequiredYes

Specific value: "OpenAiSpeech"

2. Property text_to_speech_model

Title: Text To Speech Model

Typeenum (of string)
RequiredNo
Default"tts-1-hd"

Description: The model to use for text to speech.

Must be one of:

  • “tts-1”
  • “tts-1-hd”

3. Property text_to_speech_voice

Title: Text To Speech Voice

Typeenum (of string)
RequiredNo
Default"alloy"

Description: The voice to use for text to speech.

Must be one of:

  • “alloy”
  • “echo”
  • “fable”
  • “onyx”
  • “nova”
  • “shimmer”

4. Property speech_to_text_model

Title: Speech To Text Model

Typeconst
RequiredNo
Default"whisper-1"

Description: The model to use for speech to text.

Must be one of:

  • “whisper-1” Specific value: "whisper-1"

5. Property speech_to_text_temperature

Title: Speech To Text Temperature

Typenumber
RequiredNo
Default0.3

Description: The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.