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 --upgrade --quiet elevenlabs
import os
os.environ["ELEVEN_API_KEY"] = ""
Usage
from langchain_community.tools import ElevenLabsText2SpeechTool
text_to_speak = "Hello world! I am the real slim shady"
tts = ElevenLabsText2SpeechTool()
tts.name
API Reference:
'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_openai import OpenAI
API Reference:
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.")
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3mAction:
{ "action": "eleven_labs_text2speech", "action_input": { "query": "Why did the chicken cross the playground? To get to the other slide!" } }
[0m
Observation: [36;1m[1;3m/tmp/tmpsfg783f1.wav[0m
Thought:[32;1m[1;3m I have the audio file ready to be sent to the human
Action:
{ "action": "Final Answer", "action_input": "/tmp/tmpsfg783f1.wav" }
[0m
[1m> Finished chain.[0m
tts.play(audio_file)