diff --git a/dictionary.txt b/dictionary.txt index 8036f6819..8af2f3b8e 100644 --- a/dictionary.txt +++ b/dictionary.txt @@ -228,9 +228,12 @@ EC2 preflight nav MacOS +quantized [0-9]+px ^.+[-:_]\w+$ [a-z]+([A-Z0-9]|[A-Z0-9]\w+) ([A-Z][a-z0-9]+)((\d)|([A-Z0-9][a-z0-9]+))*([A-Z])? ([a-zA-Z0-9]+\.[a-zA-Z0-9]+)+ +^([0-9]+) +^\d+B$ \..+️ diff --git a/docs/guides/python/ai-podcast-part-1.mdx b/docs/guides/python/ai-podcast-part-1.mdx index 9ec9d8cd1..f7553e44e 100644 --- a/docs/guides/python/ai-podcast-part-1.mdx +++ b/docs/guides/python/ai-podcast-part-1.mdx @@ -382,6 +382,9 @@ async def do_download_audio_model(ctx: MessageContext): @main_api.post("/download-model") async def download_audio(ctx: HttpContext): model_id = ctx.req.query.get("model", audio_model_id) + + if isinstance(model_id, list): + model_id = model_id[0] # asynchronously download the model await download_audio_model.publish({ "model_id": model_id }) @@ -662,7 +665,7 @@ nitric stack new test aws This will generate a nitric stack file called `test` which defines how we want to deploy a stack to AWS. We can update this stack file with settings to configure our batch service and the AWS Compute environment it will run in. ```yaml title: nitric.test.yaml -provider: nitric/aws@1.14.2 +provider: nitric/aws@1.15.4 # The target aws region to deploy to # See available regions: # https://docs.aws.amazon.com/general/latest/gr/lambda-service.html @@ -747,4 +750,4 @@ You can see the status of your batch jobs in the [AWS Batch console](https://con ## Next steps -In part two of this guide we'll look at adding an LLM agent to our project to automatically generate scripts for our podcasts from small prompts. +In [part two](./ai-podcast-part-2) of this guide we'll look at adding an LLM agent to our project to automatically generate scripts for our podcasts from small prompts. diff --git a/docs/guides/python/ai-podcast-part-2.mdx b/docs/guides/python/ai-podcast-part-2.mdx new file mode 100644 index 000000000..7d37fd1fd --- /dev/null +++ b/docs/guides/python/ai-podcast-part-2.mdx @@ -0,0 +1,455 @@ +--- +description: 'Using Llama 3.2 to generate podcast scripts from prompts and transform them into audio.' +tags: + - AI & Machine Learning +languages: + - python +image: /docs/images/guides/ai-podcast/part-2/banner.png +image_alt: 'AI Podcast Part 2 Banner' +featured: + image: /docs/images/guides/ai-podcast/part-2/featured.png + image_alt: 'AI Podcast Part 2 featured image' +published_at: 2024-11-07 +--- + +# Building AI Workflows: Combining LLMs and Voice Models - Part 2 + +This is part two of a two-part guide on building an AI podcast using Nitric. In this part of the guide we'll enhance [Part 1](/guides/python/ai-podcast-part-1) to complete our fully autonomous AI podcast, adding an LLM for script writing to the existing text-to-speech model. + +In this guide we'll build a fully autonomous AI podcast, combining an LLM for script writing and a text-to-speech model to produce the audio content. By the end of this guide we'll be able to produce podcast style audio content from simple text prompts like "a 10 minute podcast about [add your topic here]". + +In this first part we'll focused on generating the audio content, in this part we'll add an LLM agent to our project to automatically generate scripts for our podcasts from small prompts. Here's an example of what we'll be able to generate from a prompt requesting a podcast about "Daylight Saving Time": + +