AgentMark supports generating speech using speech prompts. Speech prompts are defined by specifying speech_config in the speech prompt’s frontmatter.

​
Example Configuration

example.prompt.mdx
---
name: speech
speech_config:
  model_name: tts-1-hd
  voice: "nova"
  speed: 1.0
  output_format: "mp3"
---

<System>
Please read this text aloud.
</System>

<SpeechPrompt>
This is a test for the speech prompt to be spoken aloud.
</SpeechPrompt>

​
Tags

TagDescription
<SpeechPrompt>Text to speech input
<System>System-level instructions

​
Available Configuration

PropertyTypeDescriptionOptional/Required
model_namestringThe name of the model to use for speech generation.Required
textstringThe text content to be converted to speech.Required
voicestringThe voice to use for speech synthesis.Optional
output_formatstringThe format of the audio output.Optional
instructionsstringAdditional instructions for speech generation.Optional
speednumberThe speed of the generated audio.Optional

Have Questions?

We’re here to help! Choose the best way to reach us: