Name | llama-index-readers-assemblyai JSON |
Version |
0.2.0
JSON |
| download |
home_page | None |
Summary | llama-index readers assemblyai integration |
upload_time | 2024-08-22 05:47:17 |
maintainer | patrickloeber |
docs_url | None |
author | Your Name |
requires_python | <4.0,>=3.8.1 |
license | MIT |
keywords |
|
VCS |
|
bugtrack_url |
|
requirements |
No requirements were recorded.
|
Travis-CI |
No Travis.
|
coveralls test coverage |
No coveralls.
|
# AssemblyAI Audio Transcript Loader
```bash
pip install llama-index-readers-assemblyai
```
The AssemblyAI Audio Transcript Loader allows to transcribe audio files with the [AssemblyAI API](https://www.assemblyai.com/) and loads the transcribed text into documents.
To use it, you should have the `assemblyai` python package installed, and the environment variable `ASSEMBLYAI_API_KEY` set with your API key. Alternatively, the API key can also be passed as an argument.
More info about AssemblyAI:
- [Website](https://www.assemblyai.com/)
- [Get a Free API key](https://www.assemblyai.com/dashboard/signup)
- [AssemblyAI API Docs](https://www.assemblyai.com/docs)
## Usage
The `AssemblyAIAudioTranscriptReader` needs at least the `file_path` argument. Audio files can be specified as an URL or a local file path.
```python
from llama_index.readers.assemblyai import AssemblyAIAudioTranscriptReader
audio_file = "https://storage.googleapis.com/aai-docs-samples/nbc.mp3"
# or a local file path: audio_file = "./nbc.mp3"
reader = AssemblyAIAudioTranscriptReader(file_path=audio_file)
docs = reader.load_data()
```
Note: Calling `reader.load_data()` blocks until the transcription is finished.
The transcribed text is available in the `text`:
```python
docs[0].text
# "Load time, a new president and new congressional makeup. Same old ..."
```
The `metadata` contains the full JSON response with more meta information:
```python
docs[0].metadata
# {'language_code': <LanguageCode.en_us: 'en_us'>,
# 'audio_url': 'https://storage.googleapis.com/aai-docs-samples/nbc.mp3',
# 'punctuate': True,
# 'format_text': True,
# ...
# }
```
## Transcript Formats
You can specify the `transcript_format` argument for different formats.
Depending on the format, one or more documents are returned. These are the different `TranscriptFormat` options:
- `TEXT`: One document with the transcription text
- `SENTENCES`: Multiple documents, splits the transcription by each sentence
- `PARAGRAPHS`: Multiple documents, splits the transcription by each paragraph
- `SUBTITLES_SRT`: One document with the transcript exported in SRT subtitles format
- `SUBTITLES_VTT`: One document with the transcript exported in VTT subtitles format
```python
from llama_index.readers.assemblyai import TranscriptFormat
reader = AssemblyAIAudioTranscripReader(
file_path="./your_file.mp3",
transcript_format=TranscriptFormat.SENTENCES,
)
docs = reader.load_data()
```
# Transcription Config
You can also specify the `config` argument to use different audio intelligence models.
Visit the [AssemblyAI API Documentation](https://www.assemblyai.com/docs) to get an overview of all available models!
```python
import assemblyai as aai
config = aai.TranscriptionConfig(
speaker_labels=True, auto_chapters=True, entity_detection=True
)
reader = AssemblyAIAudioTranscriptReader(
file_path="./your_file.mp3", config=config
)
```
## Pass the API Key as argument
Next to setting the API key as environment variable `ASSEMBLYAI_API_KEY`, it is also possible to pass it as argument.
```python
reader = AssemblyAIAudioTranscriptReader(
file_path="./your_file.mp3", api_key="YOUR_KEY"
)
```
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-index-readers-assemblyai",
"maintainer": "patrickloeber",
"docs_url": null,
"requires_python": "<4.0,>=3.8.1",
"maintainer_email": null,
"keywords": null,
"author": "Your Name",
"author_email": "you@example.com",
"download_url": "https://files.pythonhosted.org/packages/9f/97/55dd123a44171c6a2639c515da5a9a366cfba3895dfd8c04cef1f50bb3e2/llama_index_readers_assemblyai-0.2.0.tar.gz",
"platform": null,
"description": "# AssemblyAI Audio Transcript Loader\n\n```bash\npip install llama-index-readers-assemblyai\n```\n\nThe AssemblyAI Audio Transcript Loader allows to transcribe audio files with the [AssemblyAI API](https://www.assemblyai.com/) and loads the transcribed text into documents.\n\nTo use it, you should have the `assemblyai` python package installed, and the environment variable `ASSEMBLYAI_API_KEY` set with your API key. Alternatively, the API key can also be passed as an argument.\n\nMore info about AssemblyAI:\n\n- [Website](https://www.assemblyai.com/)\n- [Get a Free API key](https://www.assemblyai.com/dashboard/signup)\n- [AssemblyAI API Docs](https://www.assemblyai.com/docs)\n\n## Usage\n\nThe `AssemblyAIAudioTranscriptReader` needs at least the `file_path` argument. Audio files can be specified as an URL or a local file path.\n\n```python\nfrom llama_index.readers.assemblyai import AssemblyAIAudioTranscriptReader\n\naudio_file = \"https://storage.googleapis.com/aai-docs-samples/nbc.mp3\"\n# or a local file path: audio_file = \"./nbc.mp3\"\n\nreader = AssemblyAIAudioTranscriptReader(file_path=audio_file)\n\ndocs = reader.load_data()\n```\n\nNote: Calling `reader.load_data()` blocks until the transcription is finished.\n\nThe transcribed text is available in the `text`:\n\n```python\ndocs[0].text\n# \"Load time, a new president and new congressional makeup. Same old ...\"\n```\n\nThe `metadata` contains the full JSON response with more meta information:\n\n```python\ndocs[0].metadata\n# {'language_code': <LanguageCode.en_us: 'en_us'>,\n# 'audio_url': 'https://storage.googleapis.com/aai-docs-samples/nbc.mp3',\n# 'punctuate': True,\n# 'format_text': True,\n# ...\n# }\n```\n\n## Transcript Formats\n\nYou can specify the `transcript_format` argument for different formats.\n\nDepending on the format, one or more documents are returned. These are the different `TranscriptFormat` options:\n\n- `TEXT`: One document with the transcription text\n- `SENTENCES`: Multiple documents, splits the transcription by each sentence\n- `PARAGRAPHS`: Multiple documents, splits the transcription by each paragraph\n- `SUBTITLES_SRT`: One document with the transcript exported in SRT subtitles format\n- `SUBTITLES_VTT`: One document with the transcript exported in VTT subtitles format\n\n```python\nfrom llama_index.readers.assemblyai import TranscriptFormat\n\nreader = AssemblyAIAudioTranscripReader(\n file_path=\"./your_file.mp3\",\n transcript_format=TranscriptFormat.SENTENCES,\n)\n\ndocs = reader.load_data()\n```\n\n# Transcription Config\n\nYou can also specify the `config` argument to use different audio intelligence models.\n\nVisit the [AssemblyAI API Documentation](https://www.assemblyai.com/docs) to get an overview of all available models!\n\n```python\nimport assemblyai as aai\n\nconfig = aai.TranscriptionConfig(\n speaker_labels=True, auto_chapters=True, entity_detection=True\n)\n\nreader = AssemblyAIAudioTranscriptReader(\n file_path=\"./your_file.mp3\", config=config\n)\n```\n\n## Pass the API Key as argument\n\nNext to setting the API key as environment variable `ASSEMBLYAI_API_KEY`, it is also possible to pass it as argument.\n\n```python\nreader = AssemblyAIAudioTranscriptReader(\n file_path=\"./your_file.mp3\", api_key=\"YOUR_KEY\"\n)\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "llama-index readers assemblyai integration",
"version": "0.2.0",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "49335aa0553e06a55144f8a75f4e08823167ca5b18eaeb043802ba4fda890655",
"md5": "3cc67b16f62952454396b8aeb5566cd8",
"sha256": "8b0878c273509c60a49a1ab3dbae90d48aa3bdefd441011b013658c47cb7aeb4"
},
"downloads": -1,
"filename": "llama_index_readers_assemblyai-0.2.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "3cc67b16f62952454396b8aeb5566cd8",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.8.1",
"size": 4065,
"upload_time": "2024-08-22T05:47:16",
"upload_time_iso_8601": "2024-08-22T05:47:16.877364Z",
"url": "https://files.pythonhosted.org/packages/49/33/5aa0553e06a55144f8a75f4e08823167ca5b18eaeb043802ba4fda890655/llama_index_readers_assemblyai-0.2.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "9f9755dd123a44171c6a2639c515da5a9a366cfba3895dfd8c04cef1f50bb3e2",
"md5": "11028e050c85bec5bdbe3fa04df31e63",
"sha256": "7050753cb7d502d5ec3228203870eacb563dcc2b8778e893f4c08ddd00a13668"
},
"downloads": -1,
"filename": "llama_index_readers_assemblyai-0.2.0.tar.gz",
"has_sig": false,
"md5_digest": "11028e050c85bec5bdbe3fa04df31e63",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.8.1",
"size": 3604,
"upload_time": "2024-08-22T05:47:17",
"upload_time_iso_8601": "2024-08-22T05:47:17.787398Z",
"url": "https://files.pythonhosted.org/packages/9f/97/55dd123a44171c6a2639c515da5a9a366cfba3895dfd8c04cef1f50bb3e2/llama_index_readers_assemblyai-0.2.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-08-22 05:47:17",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-readers-assemblyai"
}