Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 22 additions & 0 deletions fern/docs.yml
Original file line number Diff line number Diff line change
Expand Up @@ -83,6 +83,9 @@ navigation:
- page: Model selection
path: pages/02-speech-to-text/pre-recorded-audio/select-the-speech-model-with-best-and-nano.mdx
slug: select-the-speech-model
- page: Select the region
path: pages/02-speech-to-text/pre-recorded-audio/select-the-region.mdx
slug: select-the-region
- page: Prompting
path: pages/02-speech-to-text/pre-recorded-audio/prompt-engineering.mdx
slug: prompting
Expand All @@ -100,6 +103,9 @@ navigation:
path: pages/02-speech-to-text/pre-recorded-audio/custom-spelling.mdx
- page: Word search
path: pages/02-speech-to-text/pre-recorded-audio/word-search.mdx
- page: Set the start and end of the transcript
path: pages/02-speech-to-text/pre-recorded-audio/set-the-start-and-end-of-the-transcript.mdx
slug: set-the-start-and-end-of-the-transcript
- section: Transcription operations
skip-slug: true
contents:
Expand Down Expand Up @@ -1555,3 +1561,19 @@ redirects:
destination: /docs/getting-started/universal-3-pro
- source: /docs/pre-recorded-audio/prompt-engineering
destination: /docs/pre-recorded-audio/prompting
- source: /docs/speech-to-text/pre-recorded-audio/improving-transcript-accuracy
destination: /docs/pre-recorded-audio/keyterms-prompting
- source: /docs/speech-to-text/pre-recorded-audio/automatic-language-detection
destination: /docs/pre-recorded-audio/language-detection
- source: /docs/pre-recorded-audio/automatic-language-detection
destination: /docs/pre-recorded-audio/language-detection
- source: /docs/pre-recorded-audio/improving-transcript-accuracy
destination: /docs/pre-recorded-audio/keyterms-prompting
- source: /playground/source
destination: https://www.assemblyai.com/dashboard/playground
- source: /docs/speech-to-text/pre-recorded-audio/word-level-timestamps
destination: /docs/pre-recorded-audio/transcript-export-options
- source: /docs/pre-recorded-audio/export-paragraphs-and-sentences
destination: /docs/pre-recorded-audio/transcript-export-options
- source: /docs/speech-to-text/pre-recorded-audio/set-language-manually
destination: https://www.assemblyai.com/docs/pre-recorded-audio/language-detection#set-language-manually
2 changes: 1 addition & 1 deletion fern/pages/02-speech-to-text/pipecat-intro-guide.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -428,7 +428,7 @@ When your voice agent is working well in development, it's time to deploy it to

**Pipecat Cloud**

Pipecat offers a managed cloud service for deploying voice agents at scale. See [Pipecat Cloud](https://pipecat.ai/cloud) for managed infrastructure that handles scaling, monitoring, and deployment automatically.
Pipecat offers a managed cloud service for deploying voice agents at scale. See [Pipecat Cloud](https://www.daily.co/products/pipecat-cloud/) for managed infrastructure that handles scaling, monitoring, and deployment automatically.

**Self-Hosting**

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ To complete this tutorial, you need:
- [Python](https://www.python.org/) installed.
- A <a href="https://www.assemblyai.com/dashboard/signup" target="_blank">free AssemblyAI account</a>.

The entire source code of this guide can be viewed [here](https://github.com/AssemblyAI/cookbook/blob/master/core-transcription/automatic-language-detection-separate.ipynb).
The entire source code of this guide can be viewed [here](/docs/guides/automatic-language-detection-separate).

## Step-by-step instructions

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -171,7 +171,7 @@ Here are helpful things to know when migrating your audio input handling:

- There's no need to specify the audio format to AssemblyAI - it's auto-detected. AssemblyAI accepts almost every audio/video file type: [here is a full list of all our supported file types](/docs/faq/what-audio-and-video-file-types-are-supported-by-your-api)
- Our SDK handles file upload and transcription automatically in one step
- For S3 files, you'll need to generate pre-signed URLs ([see example in cookbook](https://github.com/AssemblyAI/cookbook/blob/master/core-transcription/transcribe_from_s3.ipynb))
- For S3 files, you'll need to generate pre-signed URLs ([see example in cookbook](/docs/guides/transcribe_from_s3))

## Basic Transcription

Expand Down Expand Up @@ -223,7 +223,7 @@ Here are helpful things to know about our `transcribe` method:
- The SDK handles polling under the hood
- Transcript is directly accessible via `transcript.text`
- English is the default language if none is specified
- We have a [cookbook for error handling common errors](https://github.com/AssemblyAI/cookbook/blob/master/core-transcription/common_errors_and_solutions.md) when using our API.
- We have a [cookbook for error handling common errors](/docs/guides/common_errors_and_solutions) when using our API.

## Adding Features

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -152,7 +152,7 @@ Server errors rarely happen but can occasionally occur on our side.
}
```

Our API requires a publicly accessible URL that points to an audio file to retrieve your file for transcription. To transcribe a YouTube video, [check out this Cookbook](https://github.com/AssemblyAI/cookbook/blob/master/core-transcription/transcribe_youtube_videos.ipynb).
Our API requires a publicly accessible URL that points to an audio file to retrieve your file for transcription. To transcribe a YouTube video, [check out this Cookbook](/docs/guides/transcribe_youtube_videos).

##### Attempting to transcribe audio files that are not accessible

Expand All @@ -167,7 +167,7 @@ Our API requires a publicly accessible URL that points to an audio file to retri
**Solution**:

- **Public Access**: Verify that the audio file URL is publicly accessible. Our servers cannot transcribe audio from private or restricted URLs.
- **Google Drive URLs**: For audio stored on Google Drive, consult our [Google Drive Transcription Cookbook](https://github.com/AssemblyAI/cookbook/blob/master/core-transcription/transcribing-google-drive-file.md) to correctly format your URLs for access.
- **Google Drive URLs**: For audio stored on Google Drive, consult our [Google Drive Transcription Cookbook](/docs/guides/transcribing-google-drive-file) to correctly format your URLs for access.
- **Direct Upload**: Utilize the [AssemblyAI Upload endpoint](https://www.assemblyai.com/docs/api-reference/upload) to upload files directly from your device, eliminating the need for a public URL.
- **AWS S3 Pre-signed URLs**: [This Cookbook](https://github.com/AssemblyAI/cookbook/blob/master/core-transcription/transcribe_from_s3.ipynb) shows you how to use pre-signed URLs for AWS S3 storage to provide secure, temporary access for transcription without making your files public.

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -153,7 +153,7 @@ Here are helpful things to know about our `transcribe` method:
- The SDK handles polling under the hood
- Transcript is directly accessible via `transcript.text`
- English is the default language and Universal is the default speech model if none is specified
- We have a [cookbook for error handling common errors](https://github.com/AssemblyAI/cookbook/blob/master/core-transcription/common_errors_and_solutions.md) when using our API.
- We have a [cookbook for error handling common errors](/docs/guides/common_errors_and_solutions) when using our API.

## Installation

Expand Down Expand Up @@ -264,7 +264,7 @@ Here are helpful things to know when migrating your audio input handling:

- There's no need to specify the audio format to AssemblyAI - it's auto-detected. AssemblyAI accepts almost every audio/video file type: [here is a full list of all our supported file types](/docs/faq/what-audio-and-video-file-types-are-supported-by-your-api)
- Our SDK handles file upload and transcription automatically in one step
- For S3 files, you'll need to generate pre-signed URLs ([see example in cookbook](https://github.com/AssemblyAI/cookbook/blob/master/core-transcription/transcribe_from_s3.ipynb))
- For S3 files, you'll need to generate pre-signed URLs ([see example in cookbook](/docs/guides/transcribe_from_s3))

## Adding Features

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -149,7 +149,7 @@ transcript = transcriber.transcribe(presigned_url)
Here are helpful things to know when migrating your audio input handling:

- There's no need to specify the audio encoding format when using AssemblyAI - we have a transcoding pipeline under the hood which works on all [supported file types](/docs/faq/what-audio-and-video-file-types-are-supported-by-your-api) so that you can get the most accurate transcription.
- You can submit a local file, URL, stream, buffer, blob, etc., directly to our transcriber. Check out some common ways you can host audio files [here](https://github.com/AssemblyAI/cookbook/blob/master/core-transcription/README.md#hosting-audio-files).
- You can submit a local file, URL, stream, buffer, blob, etc., directly to our transcriber. Check out some common ways you can host audio files [here](/docs/guides/transcribe_from_s3).
- You can transcribe audio files that are up to 10 hours long and you can transcribe multiple files in parallel. The default amount of jobs you can transcribe at once is 200 while on the PAYG plan.

## Basic Transcription
Expand Down Expand Up @@ -189,7 +189,7 @@ Here are helpful things to know about our `transcribe` method:
- The SDK handles polling under the hood.
- The full transcript is directly accessible via `transcript.text`.
- English is the default language if none is specified.
- We have a [cookbook for error handling common errors](https://github.com/AssemblyAI/cookbook/blob/master/core-transcription/common_errors_and_solutions.md) when using our API.
- We have a [cookbook for error handling common errors](/docs/guides/common_errors_and_solutions) when using our API.

## Adding Features

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,7 @@ Here are helpful things to know about our `transcribe` method:
- The SDK handles polling under the hood
- Transcript is directly accessible via `transcript.text`
- English is the default language and Universal is the default speech model if none is specified
- We have a [cookbook for error handling common errors](https://github.com/AssemblyAI/cookbook/blob/master/core-transcription/common_errors_and_solutions.md) when using our API.
- We have a [cookbook for error handling common errors](/docs/guides/common_errors_and_solutions) when using our API.

## Installation

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ The overall process looks like this:

## Prerequisites

First, you'll need an AssemblyAI account. You can sign up [here](https://app.assemblyai.com/signup) for a free account if you don't already have one.
First, you'll need an AssemblyAI account. You can sign up [here](https://www.assemblyai.com/dashboard/signup) for a free account if you don't already have one.

Next, you'll need to **take note of your AssemblyAI API key**, which you can find on your [account dashboard](https://www.assemblyai.com/app/account) after signing in. It will be on the left-hand side of the screen under _Your API Key_.

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -158,6 +158,3 @@ for sent in transcript.get_sentences():
print()
```

# Further Documentation

Cookbook: [Translate subtitles](https://github.com/AssemblyAI/cookbook/blob/master/core-transcription/translate_subtitles.ipynb)
Loading