Skip to content

Change Batch quickstart to use new client, focus on Python SDK #222

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
J-Jaywalker wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Change Batch quickstart to use new client, focus on Python SDK #222

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ddc5971
initial commit, change python code and layout to focus on Python
Mar 6, 2026
70afc49
Add newline
Mar 10, 2026
3614f49
Move complicated output and add next steps section
Mar 10, 2026
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
20 changes: 20 additions & 0 deletions docs/speech-to-text/batch/assets/speechmatics-batch-quickstart.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
import asyncio
from speechmatics.batch import AsyncClient, TranscriptionConfig

API_KEY = "YOUR_API_KEY"
AUDIO_FILE= "example.wav"

config = TranscriptionConfig(
diarization="speaker"
)

async def main():
client = AsyncClient(api_key=API_KEY)
result = await client.transcribe(
audio_file=AUDIO_FILE,
transcription_config=config
)
print(result.transcript_text)
await client.close()

asyncio.run(main())
41 changes: 41 additions & 0 deletions docs/speech-to-text/batch/output.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,10 @@ import HTTPMethodBadge from '@site/src/theme/HTTPMethodBadge'
import checkJobStatusUnixSample from './assets/check-job-status.sh'
import checkMultipleJobsStatusUnixSample from './assets/check-multiple-jobs-status.sh'
import batchSchema from "!openapi-schema-loader!@site/spec/batch.yaml"
import transcriptResponseExample from "./assets/transcript-response-example.json?raw"
import { HelpCircle, BookOpen, FileAudio } from "lucide-react"
import { Card, Link, Text, Flex, Button, Box, Grid } from '@radix-ui/themes'
import { LinkCard } from "@site/src/theme/LinkCard";

# Output

Expand Down Expand Up @@ -118,6 +122,43 @@ Please refer to our [API Reference](/api-ref/batch/get-the-transcript-for-a-tran

<SchemaNode schema={batchSchema.paths["/jobs/{jobid}/transcript"].get.responses["200"].schema} />

### Example response

The following is an example of a transcript response, which you should see as an output of the provided [example.wav](https://github.com/speechmatics/speechmatics-js-sdk/raw/7d219bfee9166736e6aa21598535a194387b84be/examples/nodejs/example.wav) file used in the [code samples in the quickstart](/speech-to-text/batch/quickstart).

<CodeBlock language="json">
{JSON.stringify(transcriptResponseExample, null, 2)}
</CodeBlock>

## Quicklinks

<Grid columns={{initial: "1", md: "2"}} gap="3">
<LinkCard
title="Troubleshooting"
description="Resolve common issues with the Batch API"
href="/speech-to-text/batch/troubleshooting"
icon={<HelpCircle/>}
/>
<LinkCard
title="API Reference"
description="Full details about the Batch API"
href="/api-ref/batch/create-a-new-job"
icon={<BookOpen/>}
/>
<LinkCard
title="Inputs"
description="See which file types are supported"
href="/speech-to-text/batch/input"
icon={<FileAudio/>}
/>
<LinkCard
title="Limits"
description="See the limits for the Batch API"
href="/speech-to-text/batch/limits"
icon={<FileAudio/>}
/>
</Grid>

## Tracking metadata

You can optionally add tracking metadata to a job when you create it. This can be used for tracking the job through your own management workflow.
Expand Down
99 changes: 49 additions & 50 deletions docs/speech-to-text/batch/quickstart.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,11 +15,10 @@ import CodeBlock from '@theme/CodeBlock'
import { LinkCard } from "@site/src/theme/LinkCard";
import SchemaNode from "@theme/Schema";
import transcriptResponseSchema from "!openapi-schema-loader!@site/spec/batch.yaml"
import { HelpCircle, BookOpen, FileAudio } from "lucide-react"
import { HelpCircle, BookOpen, FileAudio, Users, Sparkles, Layers, BarChart2, BookMarked, Languages } from "lucide-react"

import jsQuickstart from "./assets/file-transcription-quickstart.example.js?raw"
import pythonQuickstart from "./assets/file-transcription-quickstart.py"
import transcriptResponseExample from "./assets/transcript-response-example.json?raw"
import pythonQuickstart from "./assets/speechmatics-batch-quickstart.py"

# Quickstart

Expand All @@ -42,19 +41,19 @@ Enterprise customers may need to speak to [Support](https://support.speechmatics

### 2. Pick and install a library

Check out our [JavaScript client](https://www.npmjs.com/package/@speechmatics/batch-client) or [Python client](https://pypi.org/project/speechmatics-python/) to get started.
Check out our [Batch Python client](https://github.com/speechmatics/speechmatics-python-sdk) or [JavaScript client](https://www.npmjs.com/package/@speechmatics/batch-client) to get started.

<Tabs>
<TabItem value="javascript" label="JavaScript">
Install using NPM:
<TabItem value="python" label="Python">
Install using pip:
```
npm install @speechmatics/batch-client
pip install speechmatics-batch
```
</TabItem>
<TabItem value="python" label="Python">
Install using pip:
<TabItem value="javascript" label="JavaScript">
Install using NPM:
```
pip3 install speechmatics-python
npm install @speechmatics/batch-client
```
</TabItem>
</Tabs>
Expand All @@ -68,6 +67,15 @@ Download and save our [example.wav](https://github.com/speechmatics/speechmatics
Paste your API key into `YOUR_API_KEY` in the code below.

<Tabs>
<TabItem value="python" label="Python">
<CodeBlock language="python">
{pythonQuickstart}
</CodeBlock>
You should see the following output:
```
SPEAKER S1: Welcome to Speechmatics. We're delighted that you've decided to try our speech to text software to get going. Just create an API key and submit a transcription request to our API. We hope you'll be very impressed by the results. Thank you.
```
</TabItem>
<TabItem value="javascript" label="JavaScript">
<CodeBlock language="javascript">
{jsQuickstart}
Expand All @@ -79,56 +87,47 @@ Paste your API key into `YOUR_API_KEY` in the code below.
Welcome to Speechmatics . We're delighted that you've decided to try our speech to text software to get going . Just create an API key and submit a transcription request to our API . We hope you'll be very impressed by the results . Thank you .
```
</TabItem>
<TabItem value="python" label="Python">
<CodeBlock language="python">
{pythonQuickstart}
</CodeBlock>
</TabItem>
</Tabs>

### Next Steps

### Transcript response schema

The transcript includes information about the job and metadata such as the transcription configuration that was used.

Please refer to our [API Reference](/api-ref/batch/get-the-transcript-for-a-transcription-job#responses) for full details about the transcript contents.

<SchemaNode schema={transcriptResponseSchema.paths["/jobs/{jobid}/transcript"].get.responses["200"].schema} />


### Example response

The following is an example of a transcript response, which you should see as an output of the provided [example.wav](https://github.com/speechmatics/speechmatics-js-sdk/raw/7d219bfee9166736e6aa21598535a194387b84be/examples/nodejs/example.wav) file used in the [code samples above](#4-insert-api-key).

<CodeBlock language="json">
{JSON.stringify(transcriptResponseExample, null, 2)}
</CodeBlock>

## Quicklinks
Now that you have a basic transcription working, explore these features to get more out of your audio.

<Grid columns={{initial: "1", md: "2"}} gap="3">
<LinkCard
title="Troubleshooting"
description="Resolve common issues with the Batch API"
href="/speech-to-text/batch/troubleshooting"
icon={<HelpCircle/>}
title="Speaker Diarization"
description="Identify who said what by labeling each speaker in your transcript"
href="/speech-to-text/batch/batch-diarization"
icon={<Users/>}
/>
<LinkCard
title="Custom Dictionary"
description="Boost transcription accuracy with domain-specific vocabulary"
href="/speech-to-text/features/custom-dictionary"
icon={<BookMarked/>}
/>
<LinkCard
title="Summarization"
description="Automatically generate concise summaries of your transcripts"
href="/speech-to-text/batch/speech-intelligence/summarization"
icon={<Sparkles/>}
/>
<LinkCard
title="API Reference"
description="Full details about the Batch API"
href="/api-ref/batch/create-a-new-job"
icon={<BookOpen/>}
title="Sentiment Analysis"
description="Detect the sentiment and emotional tone within your transcripts"
href="/speech-to-text/batch/speech-intelligence/sentiment-analysis"
icon={<BarChart2/>}
/>
<LinkCard
title="Inputs"
description="See which file types are supported"
href="/speech-to-text/batch/input"
icon={<FileAudio/>}
title="Auto Chapters"
description="Segment long transcripts into meaningful, titled chapters"
href="/speech-to-text/batch/speech-intelligence/auto-chapters"
icon={<Layers/>}
/>
<LinkCard
title="Limits"
description="See the limits for the Batch API"
href="/speech-to-text/batch/limits"
icon={<FileAudio/>}
title="Translation"
description="Translate your transcripts into other languages automatically"
href="/speech-to-text/features/translation"
icon={<Languages/>}
/>
</Grid>
</Grid>