Skip to main content

Eleven Labs Text2Speech

This notebook shows how to interact with the ElevenLabs API to achieve text-to-speech capabilities.

First, you need to set up an ElevenLabs account. You can follow the instructions here.

# !pip install elevenlabs
import os

os.environ["ELEVEN_API_KEY"] = ""

Usage​

from langchain.tools import ElevenLabsText2SpeechTool

text_to_speak = "Hello world! I am the real slim shady"

tts = ElevenLabsText2SpeechTool()
tts.name
    'eleven_labs_text2speech'

We can generate audio, save it to the temporary file and then play it.

speech_file = tts.run(text_to_speak)
tts.play(speech_file)

Or stream audio directly.

tts.stream_speech(text_to_speak)

Use within an Agent​

from langchain.agents import AgentType, initialize_agent, load_tools
from langchain.llms import OpenAI
llm = OpenAI(temperature=0)
tools = load_tools(["eleven_labs_text2speech"])
agent = initialize_agent(
    tools=tools,
    llm=llm,
    agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION,
    verbose=True,
)
audio_file = agent.run("Tell me a joke and read it out for me.")
    
    
    > Entering new AgentExecutor chain...
    Action:
    ```
    {
      "action": "eleven_labs_text2speech",
      "action_input": {
        "query": "Why did the chicken cross the playground? To get to the other slide!"
      }
    }
    ```
    
    
    Observation: /tmp/tmpsfg783f1.wav
    Thought: I have the audio file ready to be sent to the human
    Action:
    ```
    {
      "action": "Final Answer",
      "action_input": "/tmp/tmpsfg783f1.wav"
    }
    ```
    
    
    
    > Finished chain.
tts.play(audio_file)