| Name | elevenlabs-haystack JSON |
| Version |
0.4.5
JSON |
| download |
| home_page | None |
| Summary | ElevenLabs Text-to-Speech components for Haystack. |
| upload_time | 2024-10-17 19:00:37 |
| maintainer | None |
| docs_url | None |
| author | Andy |
| requires_python | <4.0,>=3.8 |
| license | None |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# ElevenLabs Haystack Integration
This repository contains an integration of ElevenLabs' Text-to-Speech API with Haystack pipelines. This package allows you to convert text to speech using ElevenLabs' API and optionally save the generated audio to AWS S3.
## Installation
```bash
pip install elevenlabs_haystack
```
## Setting Up API Keys
#### **ElevenLabs API Key**
To access the ElevenLabs API, you need to create an account and obtain an API key.
1. Go to the [ElevenLabs](https://elevenlabs.ai/) website and sign up for an account.
2. Once logged in, navigate to the **Profile** section.
3. In the **API** section, generate a new API key.
4. Copy the API key.
#### **AWS Credentials**
To store generated audio files on AWS S3, you need AWS credentials (Access Key ID, Secret Access Key) and specify a region.
1. If you don’t have an AWS account, sign up at [AWS](https://aws.amazon.com/).
2. Create a new IAM user and assign the necessary permissions to allow the user to upload files to S3. The `AmazonS3FullAccess` policy is sufficient for this example.
3. Once the IAM user is created, download or note the **AWS Access Key ID** and **Secret Access Key**.
4. Identify the **AWS Region** where your S3 bucket resides (e.g., `us-east-1`). This information can be found in the AWS Management Console.
5. Finally, create or identify the S3 bucket where the generated audio files will be saved.
Create a `.env` file in the root directory with the following content (replace with your actual credentials):
```bash
ELEVENLABS_API_KEY=sk_your_elevenlabs_api_key_here
AWS_ACCESS_KEY_ID=your_aws_access_key_id
AWS_SECRET_ACCESS_KEY=your_aws_secret_access_key
AWS_REGION_NAME=us-east-1
AWS_S3_BUCKET_NAME=your_s3_bucket_name
```
These variables will be automatically loaded using `dotenv` and used to access ElevenLabs and AWS services securely.
## Usage
### Basic Text-to-Speech Example
This example shows how to use the `ElevenLabsTextToSpeech` component to convert text to speech and save the generated audio file locally or in an AWS S3 bucket. It uses environment variables to access sensitive credentials.
```python
from haystack.utils import Secret
from elevenlabs_haystack import ElevenLabsTextToSpeech
# Initialize the ElevenLabsTextToSpeech component using environment variables for sensitive data
tts = ElevenLabsTextToSpeech(
elevenlabs_api_key=Secret.from_env_var("ELEVENLABS_API_KEY"),
output_folder="audio_files", # Save the generated audio locally
voice_id="Xb7hH8MSUJpSbSDYk0k2", # ElevenLabs voice ID (Alice)
aws_s3_bucket_name=Secret.from_env_var("AWS_S3_BUCKET_NAME"), # S3 bucket for optional upload
aws_s3_output_folder="s3_files", # Save the generated audio to AWS S3
aws_access_key_id=Secret.from_env_var("AWS_ACCESS_KEY_ID"),
aws_secret_access_key=Secret.from_env_var("AWS_SECRET_ACCESS_KEY"),
aws_region_name=Secret.from_env_var("AWS_REGION_NAME"), # AWS region
voice_settings={
"stability": 0.75,
"similarity_boost": 0.75,
"style": 0.5,
"use_speaker_boost": True, # Optional voice settings
},
)
# Run the text-to-speech conversion
result = tts.run("Hello, world!")
# Print the result
print(result)
"""
{
"id": "elevenlabs-id",
"file_name": "audio_files/elevenlabs-id.mp3",
"s3_file_name": "s3_files/elevenlabs-id.mp3",
"s3_bucket_name": "test-bucket",
"s3_presigned_url": "https://test-bucket.s3.amazonaws.com/s3_files/elevenlabs-id.mp3"
}
"""
```
### Example Using Haystack Pipeline
This example demonstrates how to integrate the `ElevenLabsTextToSpeech` component into a Haystack pipeline. Additionally, we define a `WelcomeTextGenerator` component that generates a personalized welcome message.
```python
from haystack import component, Pipeline
from haystack.utils import Secret
from elevenlabs_haystack import ElevenLabsTextToSpeech
# Define a simple component to generate a welcome message
@component
class WelcomeTextGenerator:
"""
A component generating a personal welcome message and making it upper case.
"""
@component.output_types(welcome_text=str, note=str)
def run(self, name: str):
return {
"welcome_text": f'Hello {name}, welcome to Haystack!'.upper(),
"note": "welcome message is ready"
}
# Create a Pipeline
text_pipeline = Pipeline()
# Add WelcomeTextGenerator to the Pipeline
text_pipeline.add_component(
name="welcome_text_generator",
instance=WelcomeTextGenerator()
)
# Add ElevenLabsTextToSpeech to the Pipeline using environment variables
text_pipeline.add_component(
name="tts",
instance=ElevenLabsTextToSpeech(
elevenlabs_api_key=Secret.from_env_var("ELEVENLABS_API_KEY"),
output_folder="audio_files", # Save the generated audio locally
voice_id="Xb7hH8MSUJpSbSDYk0k2", # ElevenLabs voice ID (Alice)
aws_s3_bucket_name=Secret.from_env_var("AWS_S3_BUCKET_NAME"), # S3 bucket for optional upload
aws_s3_output_folder="s3_files", # Save the generated audio to AWS S3
aws_access_key_id=Secret.from_env_var("AWS_ACCESS_KEY_ID"),
aws_secret_access_key=Secret.from_env_var("AWS_SECRET_ACCESS_KEY"),
aws_region_name=Secret.from_env_var("AWS_REGION_NAME"), # Load region from env
voice_settings={
"stability": 0.75,
"similarity_boost": 0.75,
"style": 0.5,
"use_speaker_boost": True, # Optional voice settings
},
),
)
# Connect the output of WelcomeTextGenerator to the input of ElevenLabsTextToSpeech
text_pipeline.connect(sender="welcome_text_generator.welcome_text", receiver="tts")
# Run the pipeline with a sample name
result = text_pipeline.run({"welcome_text_generator": {"name": "Bilge"}})
# Print the result
print(result)
"""
{
"id": "elevenlabs-id",
"file_name": "audio_files/elevenlabs-id.mp3",
"s3_file_name": "s3_files/elevenlabs-id.mp3",
"s3_bucket_name": "test-bucket",
"s3_presigned_url": "https://test-bucket.s3.amazonaws.com/s3_files/elevenlabs-id.mp3"
}
"""
```
## License
This project is licensed under the MIT License.
Raw data
{
"_id": null,
"home_page": null,
"name": "elevenlabs-haystack",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.8",
"maintainer_email": null,
"keywords": null,
"author": "Andy",
"author_email": "andychert@protonmail.com",
"download_url": "https://files.pythonhosted.org/packages/3d/6e/b23630610777f3ae490d0d066d937d5831abd263f68aa9a5ba8906e245c5/elevenlabs_haystack-0.4.5.tar.gz",
"platform": null,
"description": "# ElevenLabs Haystack Integration\n\nThis repository contains an integration of ElevenLabs' Text-to-Speech API with Haystack pipelines. This package allows you to convert text to speech using ElevenLabs' API and optionally save the generated audio to AWS S3.\n\n## Installation\n\n```bash\npip install elevenlabs_haystack\n```\n\n## Setting Up API Keys\n\n#### **ElevenLabs API Key**\n\nTo access the ElevenLabs API, you need to create an account and obtain an API key.\n\n1. Go to the [ElevenLabs](https://elevenlabs.ai/) website and sign up for an account.\n2. Once logged in, navigate to the **Profile** section.\n3. In the **API** section, generate a new API key.\n4. Copy the API key.\n\n#### **AWS Credentials**\n\nTo store generated audio files on AWS S3, you need AWS credentials (Access Key ID, Secret Access Key) and specify a region.\n\n1. If you don\u2019t have an AWS account, sign up at [AWS](https://aws.amazon.com/).\n2. Create a new IAM user and assign the necessary permissions to allow the user to upload files to S3. The `AmazonS3FullAccess` policy is sufficient for this example.\n3. Once the IAM user is created, download or note the **AWS Access Key ID** and **Secret Access Key**.\n4. Identify the **AWS Region** where your S3 bucket resides (e.g., `us-east-1`). This information can be found in the AWS Management Console.\n5. Finally, create or identify the S3 bucket where the generated audio files will be saved.\n\nCreate a `.env` file in the root directory with the following content (replace with your actual credentials):\n\n```bash\nELEVENLABS_API_KEY=sk_your_elevenlabs_api_key_here\nAWS_ACCESS_KEY_ID=your_aws_access_key_id\nAWS_SECRET_ACCESS_KEY=your_aws_secret_access_key\nAWS_REGION_NAME=us-east-1\nAWS_S3_BUCKET_NAME=your_s3_bucket_name\n```\n\nThese variables will be automatically loaded using `dotenv` and used to access ElevenLabs and AWS services securely.\n\n## Usage\n\n### Basic Text-to-Speech Example\n\nThis example shows how to use the `ElevenLabsTextToSpeech` component to convert text to speech and save the generated audio file locally or in an AWS S3 bucket. It uses environment variables to access sensitive credentials.\n\n```python\nfrom haystack.utils import Secret\nfrom elevenlabs_haystack import ElevenLabsTextToSpeech\n\n# Initialize the ElevenLabsTextToSpeech component using environment variables for sensitive data\ntts = ElevenLabsTextToSpeech(\n elevenlabs_api_key=Secret.from_env_var(\"ELEVENLABS_API_KEY\"),\n output_folder=\"audio_files\", # Save the generated audio locally\n voice_id=\"Xb7hH8MSUJpSbSDYk0k2\", # ElevenLabs voice ID (Alice)\n aws_s3_bucket_name=Secret.from_env_var(\"AWS_S3_BUCKET_NAME\"), # S3 bucket for optional upload\n aws_s3_output_folder=\"s3_files\", # Save the generated audio to AWS S3\n aws_access_key_id=Secret.from_env_var(\"AWS_ACCESS_KEY_ID\"),\n aws_secret_access_key=Secret.from_env_var(\"AWS_SECRET_ACCESS_KEY\"),\n aws_region_name=Secret.from_env_var(\"AWS_REGION_NAME\"), # AWS region\n voice_settings={\n \"stability\": 0.75,\n \"similarity_boost\": 0.75,\n \"style\": 0.5,\n \"use_speaker_boost\": True, # Optional voice settings\n },\n)\n\n# Run the text-to-speech conversion\nresult = tts.run(\"Hello, world!\")\n\n# Print the result\nprint(result)\n\n\"\"\"\n{\n \"id\": \"elevenlabs-id\",\n \"file_name\": \"audio_files/elevenlabs-id.mp3\",\n \"s3_file_name\": \"s3_files/elevenlabs-id.mp3\",\n \"s3_bucket_name\": \"test-bucket\",\n \"s3_presigned_url\": \"https://test-bucket.s3.amazonaws.com/s3_files/elevenlabs-id.mp3\"\n}\n\"\"\"\n```\n\n### Example Using Haystack Pipeline\n\nThis example demonstrates how to integrate the `ElevenLabsTextToSpeech` component into a Haystack pipeline. Additionally, we define a `WelcomeTextGenerator` component that generates a personalized welcome message.\n\n```python\nfrom haystack import component, Pipeline\nfrom haystack.utils import Secret\nfrom elevenlabs_haystack import ElevenLabsTextToSpeech\n\n# Define a simple component to generate a welcome message\n@component\nclass WelcomeTextGenerator:\n \"\"\"\n A component generating a personal welcome message and making it upper case.\n \"\"\"\n @component.output_types(welcome_text=str, note=str)\n def run(self, name: str):\n return {\n \"welcome_text\": f'Hello {name}, welcome to Haystack!'.upper(),\n \"note\": \"welcome message is ready\"\n }\n\n# Create a Pipeline\ntext_pipeline = Pipeline()\n\n# Add WelcomeTextGenerator to the Pipeline\ntext_pipeline.add_component(\n name=\"welcome_text_generator\",\n instance=WelcomeTextGenerator()\n)\n\n# Add ElevenLabsTextToSpeech to the Pipeline using environment variables\ntext_pipeline.add_component(\n name=\"tts\",\n instance=ElevenLabsTextToSpeech(\n elevenlabs_api_key=Secret.from_env_var(\"ELEVENLABS_API_KEY\"),\n output_folder=\"audio_files\", # Save the generated audio locally\n voice_id=\"Xb7hH8MSUJpSbSDYk0k2\", # ElevenLabs voice ID (Alice)\n aws_s3_bucket_name=Secret.from_env_var(\"AWS_S3_BUCKET_NAME\"), # S3 bucket for optional upload\n aws_s3_output_folder=\"s3_files\", # Save the generated audio to AWS S3\n aws_access_key_id=Secret.from_env_var(\"AWS_ACCESS_KEY_ID\"),\n aws_secret_access_key=Secret.from_env_var(\"AWS_SECRET_ACCESS_KEY\"),\n aws_region_name=Secret.from_env_var(\"AWS_REGION_NAME\"), # Load region from env\n voice_settings={\n \"stability\": 0.75,\n \"similarity_boost\": 0.75,\n \"style\": 0.5,\n \"use_speaker_boost\": True, # Optional voice settings\n },\n ),\n)\n\n# Connect the output of WelcomeTextGenerator to the input of ElevenLabsTextToSpeech\ntext_pipeline.connect(sender=\"welcome_text_generator.welcome_text\", receiver=\"tts\")\n\n# Run the pipeline with a sample name\nresult = text_pipeline.run({\"welcome_text_generator\": {\"name\": \"Bilge\"}})\n\n# Print the result\nprint(result)\n\n\"\"\"\n{\n \"id\": \"elevenlabs-id\",\n \"file_name\": \"audio_files/elevenlabs-id.mp3\",\n \"s3_file_name\": \"s3_files/elevenlabs-id.mp3\",\n \"s3_bucket_name\": \"test-bucket\",\n \"s3_presigned_url\": \"https://test-bucket.s3.amazonaws.com/s3_files/elevenlabs-id.mp3\"\n}\n\"\"\"\n```\n\n## License\n\nThis project is licensed under the MIT License.\n",
"bugtrack_url": null,
"license": null,
"summary": "ElevenLabs Text-to-Speech components for Haystack.",
"version": "0.4.5",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "91c20050b7faaadd0700c04e5b8f99e75f79bdfbe83ccff3f06c91d2f4092e5c",
"md5": "8743ebbd73a93c2ca20d5d59ee9b30c6",
"sha256": "7571330bd983a207ac48abae95dd5c8ef76eb6eeed6f7a8137c2293b7b00f9d1"
},
"downloads": -1,
"filename": "elevenlabs_haystack-0.4.5-py3-none-any.whl",
"has_sig": false,
"md5_digest": "8743ebbd73a93c2ca20d5d59ee9b30c6",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.8",
"size": 4876,
"upload_time": "2024-10-17T19:00:36",
"upload_time_iso_8601": "2024-10-17T19:00:36.595473Z",
"url": "https://files.pythonhosted.org/packages/91/c2/0050b7faaadd0700c04e5b8f99e75f79bdfbe83ccff3f06c91d2f4092e5c/elevenlabs_haystack-0.4.5-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "3d6eb23630610777f3ae490d0d066d937d5831abd263f68aa9a5ba8906e245c5",
"md5": "aca6bee80dc8448bbf9134183f2d9cbd",
"sha256": "bb02727bd9af1151f639dc4cbc843ef50faa30ee7cf738b54a36b425e1bb84eb"
},
"downloads": -1,
"filename": "elevenlabs_haystack-0.4.5.tar.gz",
"has_sig": false,
"md5_digest": "aca6bee80dc8448bbf9134183f2d9cbd",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.8",
"size": 4051,
"upload_time": "2024-10-17T19:00:37",
"upload_time_iso_8601": "2024-10-17T19:00:37.516150Z",
"url": "https://files.pythonhosted.org/packages/3d/6e/b23630610777f3ae490d0d066d937d5831abd263f68aa9a5ba8906e245c5/elevenlabs_haystack-0.4.5.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-10-17 19:00:37",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "elevenlabs-haystack"
}
