Legacy Prerequisites
The following reference applies only to accounts for which DesiVocal has arranged continued API support. It requires theopenai and requests libraries, a DesiVocal API key, and an OpenAI API key for the agent’s default model.
Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Reference the retired DesiVocalTools adapter and migrate text-to-speech agents to an active provider.
openai and requests libraries, a DesiVocal API key, and an OpenAI API key for the agent’s default model.
uv pip install openai requests
export DESI_VOCAL_API_KEY=***
export OPENAI_API_KEY=***
from agno.agent import Agent
from agno.tools.desi_vocal import DesiVocalTools
agent = Agent(
instructions=[
"You are a text-to-speech assistant that converts text to natural Indian voices",
"Help users generate audio from text using various Indian accents and languages",
"Provide information about available voices and their characteristics",
"Create high-quality audio content for users",
],
tools=[DesiVocalTools()],
)
agent.print_response("Convert this text to speech: 'Namaste, welcome to our service'", stream=True)
| Parameter | Type | Default | Description |
|---|---|---|---|
api_key | Optional[str] | None | Desi Vocal API key. Uses DESI_VOCAL_API_KEY if not set. |
voice_id | Optional[str] | "f27d74e5-ea71-4697-be3e-f04bbd80c1a8" | Default voice ID to use for text-to-speech. |
enable_get_voices | bool | True | Enable voice listing functionality. |
enable_text_to_speech | bool | True | Enable text-to-speech conversion functionality. |
all | bool | False | Enable all functionality when set to True. |
timeout | int | 30 | Request timeout in seconds for API calls. |
| Function | Description |
|---|---|
get_voices | Retrieve list of available voices with their IDs and details. |
text_to_speech | Convert text to speech using specified or default voice. |
Was this page helpful?