mirror of https://github.com/hwchase17/langchain
Integration with eleven labs
parent
27944cb611
commit
800fe4a73f
@ -0,0 +1,243 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "c8871563-02fe-49f2-901e-c0f05d655a6b",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"True"
|
||||
]
|
||||
},
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from dotenv import load_dotenv\n",
|
||||
"load_dotenv()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a991a6f8-1897-4f49-a191-ae3bdaeda856",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Eleven Labs Text2Speech\n",
|
||||
"\n",
|
||||
"This notebook shows how to interact with the `ElevenLabs API` to achieve text-to-speech capabilities."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "9eeb311e-e1bd-4959-8536-4d267f302eb3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"First, you need to set up an ElevenLabs account. You can follow the instructions [here](https://docs.elevenlabs.io/welcome/introduction)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "0a309c0e-5310-4eaa-8af9-bcbc252e45da",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# !pip install elevenlabs"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "f097c3b1-f761-43cb-aad0-8ba2e93e5f5f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"ELEVEN_API_KEY\"] = \"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "434b2454-2bff-484d-822c-4026a9dc1383",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Usage"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "2f57a647-9214-4562-a8cf-f263a15d1f40",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.tools import ElevenLabsText2SpeechTool\n",
|
||||
"tts = ElevenLabsText2SpeechTool()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "2ff86b69-de9d-4922-ada9-88f98b5c7569",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'eleven_labs_text2speech'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"tts.name"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "f1984844-aa75-4f83-9d42-1c8052d87cc0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"speech_file = tts.run(\"Hello world! I am real slim shady\")\n",
|
||||
"tts.play(speech_file)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "3bcced62-4e7c-40ca-95ed-0680baca3082",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a152766d-5f06-48b1-ac89-b4e8d88d3c9f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Use within an Agent"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "37626aea-0cf0-4849-9c00-c0f40515ffe0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain import OpenAI\n",
|
||||
"from langchain.agents import initialize_agent, AgentType, load_tools"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "c168f28e-d5b7-4c93-bed8-0ab317b4a44b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"tools = load_tools(['eleven_labs_text2speech'])\n",
|
||||
"agent = initialize_agent(\n",
|
||||
" tools=tools,\n",
|
||||
" llm=llm,\n",
|
||||
" agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION,\n",
|
||||
" verbose=True,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "336bf95a-3ccb-4963-aac3-638a4df2ed78",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mAction:\n",
|
||||
"```\n",
|
||||
"{\n",
|
||||
" \"action\": \"eleven_labs_text2speech\",\n",
|
||||
" \"action_input\": {\n",
|
||||
" \"query\": \"Why did the chicken cross the playground? To get to the other slide!\"\n",
|
||||
" }\n",
|
||||
"}\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m/tmp/tmp8z9e6xf6.wav\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I have the audio file ready to be played\n",
|
||||
"Action:\n",
|
||||
"```\n",
|
||||
"{\n",
|
||||
" \"action\": \"Final Answer\",\n",
|
||||
" \"action_input\": \"/tmp/tmp8z9e6xf6.wav\"\n",
|
||||
"}\n",
|
||||
"```\n",
|
||||
"\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"audio_file = agent.run(\"Tell me a joke and read it out for me.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "f0aa7aa9-4682-4599-8cae-59347d9e5210",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tts.play(audio_file)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "caffa8af-6d12-40c4-a25c-bdb28c204a09",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.16"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -0,0 +1,8 @@
|
||||
"""Eleven Labs Services Tools."""
|
||||
|
||||
from langchain.tools.eleven_labs.text2speech import (
|
||||
ElevenLabsText2SpeechTool
|
||||
)
|
||||
|
||||
|
||||
__all__ = [ElevenLabsText2SpeechTool]
|
@ -0,0 +1,86 @@
|
||||
import tempfile
|
||||
from typing import Dict
|
||||
|
||||
from langchain.pydantic_v1 import root_validator
|
||||
from langchain.tools.base import BaseTool
|
||||
from langchain.utils import get_from_dict_or_env
|
||||
|
||||
|
||||
class ElevenLabsText2SpeechTool(BaseTool):
|
||||
"""Tool that queries the Eleven Labs Text2Speech API.
|
||||
|
||||
In order to set this up, follow instructions at:
|
||||
https://docs.elevenlabs.io/welcome/introduction
|
||||
"""
|
||||
|
||||
name: str = "eleven_labs_text2speech"
|
||||
description: str = (
|
||||
"A wrapper around Eleven Labs Text2Speech. "
|
||||
"Useful for when you need to convert text to speech. "
|
||||
"It supports multiple languages, including English, German, Polish, Spanish, Italian, French, Portuguese, and Hindi. "
|
||||
)
|
||||
|
||||
@root_validator(pre=True)
|
||||
def validate_environment(cls, values: Dict) -> Dict:
|
||||
"""Validate that api key exists in environment."""
|
||||
_ = get_from_dict_or_env(
|
||||
values, "eleven_api_key", "ELEVEN_API_KEY"
|
||||
)
|
||||
|
||||
return values
|
||||
|
||||
def _text2speech(self, text: str) -> str:
|
||||
try:
|
||||
from elevenlabs import generate
|
||||
|
||||
except ImportError:
|
||||
raise ImportError(
|
||||
"elevenlabs is not installed. "
|
||||
"Run `pip install elevenlabs` to install."
|
||||
)
|
||||
|
||||
speech = generate(text=text, model='eleven_multilingual_v1')
|
||||
with tempfile.NamedTemporaryFile(
|
||||
mode="bx", suffix=".wav", delete=False
|
||||
) as f:
|
||||
f.write(speech)
|
||||
return f.name
|
||||
|
||||
def _run(self, query: str) -> str:
|
||||
"""Use the tool."""
|
||||
try:
|
||||
speech_file = self._text2speech(query)
|
||||
return speech_file
|
||||
except Exception as e:
|
||||
raise RuntimeError(f"Error while running ElevenLabsText2SpeechTool: {e}")
|
||||
|
||||
def play(self, speech_file: str) -> None:
|
||||
"""Play the text as speech."""
|
||||
try:
|
||||
from elevenlabs import play
|
||||
|
||||
except ImportError:
|
||||
raise ImportError(
|
||||
"elevenlabs is not installed. "
|
||||
"Run `pip install elevenlabs` to install."
|
||||
)
|
||||
with open(speech_file, mode="rb") as f:
|
||||
speech = f.read()
|
||||
|
||||
play(speech)
|
||||
|
||||
def stream(self, query: str) -> None:
|
||||
"""Stream the text as speech."""
|
||||
|
||||
try:
|
||||
from elevenlabs import stream, generate
|
||||
|
||||
except ImportError:
|
||||
raise ImportError(
|
||||
"elevenlabs is not installed. "
|
||||
"Run `pip install elevenlabs` to install."
|
||||
)
|
||||
|
||||
speech_stream = generate(text=query, model='eleven_multilingual_v1', stream=True)
|
||||
stream(speech_stream)
|
||||
|
Loading…
Reference in New Issue