Skip to content

feat(gladia): add GladiaTranscriber integration for audio transcription - #3751

Open
Aryan-Pardeshi wants to merge 4 commits into
deepset-ai:mainfrom
Aryan-Pardeshi:feat/gladia-integration
Open

feat(gladia): add GladiaTranscriber integration for audio transcription#3751
Aryan-Pardeshi wants to merge 4 commits into
deepset-ai:mainfrom
Aryan-Pardeshi:feat/gladia-integration

Conversation

@Aryan-Pardeshi

Copy link
Copy Markdown

Closes #2246.

Adds a gladia integration with a GladiaTranscriber component, modelled on Haystack's RemoteWhisperTranscriber as suggested in the issue.

Scoped to batch transcription over the Gladia v2 pre-recorded flow. The issue links Gladia's real-time product page while the design describes a batch component — flagging that explicitly so review does not stall on the ambiguity. Happy to follow up with streaming as a separate PR if that is what you want.

Unit tests mock httpx; no API key or network needed.

@Aryan-Pardeshi
Aryan-Pardeshi requested a review from a team as a code owner August 7, 2026 22:20
@Aryan-Pardeshi
Aryan-Pardeshi requested review from anakin87 and removed request for a team August 7, 2026 22:20
@CLAassistant

CLAassistant commented Aug 7, 2026

Copy link
Copy Markdown

CLA assistant check
All committers have signed the CLA.

@github-actions github-actions Bot added the type:documentation Improvements or additions to documentation label Aug 7, 2026
@HaystackBot

Copy link
Copy Markdown
Contributor

Hi @Aryan-Pardeshi, thanks a lot for your contribution! 🙏

We noticed that the Contributor License Agreement (CLA) check (license/cla) hasn't passed yet, so we've temporarily moved this PR to draft and paused the review assignment.

To get your PR reviewed, please sign the CLA via the link in the license/cla check below (or in the CLA bot comment). As soon as the check turns green, this PR will automatically be marked ready for review again and a reviewer will be re-assigned.

@HaystackBot
HaystackBot removed the request for review from anakin87 August 7, 2026 23:29
@HaystackBot HaystackBot added the cla-pending PR is in draft until the contributor signs the CLA label Aug 7, 2026
@HaystackBot
HaystackBot marked this pull request as draft August 7, 2026 23:29
@HaystackBot
HaystackBot marked this pull request as ready for review August 8, 2026 05:08
@HaystackBot
HaystackBot requested a review from anakin87 August 8, 2026 05:08
@HaystackBot

Copy link
Copy Markdown
Contributor

Thanks for signing the CLA, @Aryan-Pardeshi! 🎉 This PR is now ready for review again and the reviewer has been re-assigned.

@HaystackBot HaystackBot removed the cla-pending PR is in draft until the contributor signs the CLA label Aug 8, 2026

@anakin87 anakin87 left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hello!

  1. I see that several files are missing (license, py.typed, ...). Please use the scaffold script to create a new integration as suggested here
  2. Have you had the chance to try this integration yourself with an API key? This is strongly recommended before submitting a new integration.

documents = []
with httpx.Client(timeout=self.timeout) as client:
for source in sources:
audio_url = self._upload_audio(client, source)

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

For simplicity, let's use the Gladia Python SDK

Adds the files/registrations the create_new_integration.py scaffold
script normally generates but were missing from this PR: LICENSE.txt,
py.typed marker, tests/__init__.py, CI workflow
(.github/workflows/gladia.yml), labeler.yml entry, coverage-comment
workflow registration, and the root README table row.

Also adds a real (currently-skipped) integration test that transcribes
a committed sample audio file via the live Gladia API, gated on
GLADIA_API_KEY like the other integrations in this repo. It will
start running once a maintainer adds the secret.
@Aryan-Pardeshi

Copy link
Copy Markdown
Author

Thanks for the pointer — I ran scripts/create_new_integration.py and diffed it against what was in this PR. Added everything that scaffold generates but was missing: LICENSE.txt, the py.typed marker, tests/__init__.py, the CI workflow (.github/workflows/gladia.yml), the labeler.yml entry, the coverage-comment workflow registration, and the root README row.

On point 2: I don't have a Gladia API key, so I can't personally verify this against the live API. I added a real integration test (test_run_integration / test_run_async_integration) that transcribes a committed sample audio file through the actual API, gated on GLADIA_API_KEY the same way the other integrations in this repo do — it's skipped until a maintainer adds the secret, at which point CI will actually exercise it. Happy to iterate further once that's in place.

@anakin87

Copy link
Copy Markdown
Member

@Aryan-Pardeshi, I recommend checking whether Gladia provides free credits on the starter plan.

Before committing to a deep review of the implementation, I expect the contributor to have properly tested their implementation locally.

If you realize you cannot test it yourself, I think it's reasonable to close the PR.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

topic:CI type:documentation Improvements or additions to documentation

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Add new Gladia integration with a GladiaTranscriber component

4 participants