diff --git a/docs/extras/integrations/tools/eleven_labs_tts.ipynb b/docs/extras/integrations/tools/eleven_labs_tts.ipynb index cfc5f22217..7178bf8704 100644 --- a/docs/extras/integrations/tools/eleven_labs_tts.ipynb +++ b/docs/extras/integrations/tools/eleven_labs_tts.ipynb @@ -1,27 +1,5 @@ { "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", @@ -72,20 +50,9 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 6, "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": { @@ -93,33 +60,56 @@ "'eleven_labs_text2speech'" ] }, - "execution_count": 3, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ + "from langchain.tools import ElevenLabsText2SpeechTool\n", + "\n", + "text_to_speak = \"Hello world! I am the real slim shady\"\n", + "\n", + "tts = ElevenLabsText2SpeechTool()\n", "tts.name" ] }, { - "cell_type": "code", - "execution_count": 10, - "id": "f1984844-aa75-4f83-9d42-1c8052d87cc0", + "cell_type": "markdown", + "id": "d4613fed-66f0-47c6-be50-7e7670654427", "metadata": {}, - "outputs": [], "source": [ - "speech_file = tts.run(\"Hello world! I am real slim shady\")\n", - "tts.play(speech_file)" + "We can generate audio, save it to the temporary file and then play it." ] }, { "cell_type": "code", - "execution_count": null, - "id": "3bcced62-4e7c-40ca-95ed-0680baca3082", + "execution_count": 7, + "id": "f1984844-aa75-4f83-9d42-1c8052d87cc0", "metadata": {}, "outputs": [], - "source": [] + "source": [ + "speech_file = tts.run(text_to_speak)\n", + "tts.play(speech_file)" + ] + }, + { + "cell_type": "markdown", + "id": "42d89cd4-ac2a-4857-9787-c9018b4a8782", + "metadata": {}, + "source": [ + "Or stream audio directly." + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "d72822f8-3223-47e2-8d2e-6ff46b8c8645", + "metadata": {}, + "outputs": [], + "source": [ + "tts.stream(text_to_speak)" + ] }, { "cell_type": "markdown", @@ -131,7 +121,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 12, "id": "37626aea-0cf0-4849-9c00-c0f40515ffe0", "metadata": {}, "outputs": [], @@ -142,13 +132,13 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 13, "id": "c168f28e-d5b7-4c93-bed8-0ab317b4a44b", "metadata": {}, "outputs": [], "source": [ "llm = OpenAI(temperature=0)\n", - "tools = load_tools(['eleven_labs_text2speech'])\n", + "tools = load_tools([\"eleven_labs_text2speech\"])\n", "agent = initialize_agent(\n", " tools=tools,\n", " llm=llm,\n", @@ -159,7 +149,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 14, "id": "336bf95a-3ccb-4963-aac3-638a4df2ed78", "metadata": {}, "outputs": [ @@ -181,15 +171,16 @@ "```\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", + "Observation: \u001b[36;1m\u001b[1;3m/tmp/tmpsfg783f1.wav\u001b[0m\n", + "Thought:\u001b[32;1m\u001b[1;3m I have the audio file ready to be sent to the human\n", "Action:\n", "```\n", "{\n", " \"action\": \"Final Answer\",\n", - " \"action_input\": \"/tmp/tmp8z9e6xf6.wav\"\n", + " \"action_input\": \"/tmp/tmpsfg783f1.wav\"\n", "}\n", "```\n", + "\n", "\u001b[0m\n", "\n", "\u001b[1m> Finished chain.\u001b[0m\n" @@ -202,21 +193,13 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 15, "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": {