Add hidden Whisper multilingual streaming page #570
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Create new whisper-multilingual-streaming.mdx page with 99 language support - Add language detection configuration and output format documentation - Add non-speech tags section for silence and music detection - Add quickstart examples for Python SDK, Python, JavaScript SDK, and JavaScript - Add hidden page entry in docs.yml under multilingual transcription Co-Authored-By: Ryan Seams <ryan.seams@gmail.com>
Contributor
Author
🤖 Devin AI EngineerI'll be helping with this pull request! Here's what you should know: ✅ I will automatically:
Note: I can only respond to comments from users who have write access to this repository. ⚙️ Control Options:
|
- Add hyperlink to WhisperLiveKit package in intro - Update supported languages to correct 99 language list with codes - Replace language list with table showing code and language name - Update formatting section to explain format_turns requirement - Add latency tradeoff guidance (off for voice agents, on for notetaking) - Add formatted vs unformatted example comparison Co-Authored-By: Ryan Seams <ryan.seams@gmail.com>
- Make supported languages table collapsible with Accordion - Update sample rate to 48000 and FRAMES_PER_BUFFER to 3200 to match multilingual quickstart - Reorder tabs to make Python the default shown option Co-Authored-By: Ryan Seams <ryan.seams@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Adds a new hidden documentation page for Whisper multilingual streaming under the Universal Streaming section. The page documents the
whisper-streamingspeech model which supports 99 languages with automatic language detection.Key sections include:
speech_model: "whisper-streaming"language_codeandlanguage_confidenceresponse fields[Silence],[Music]detectionThe page is placed directly under "Multilingual transcription" in the navigation and marked as hidden.
Review & Testing Checklist for Human
pnpm docslocally and navigate to/docs/universal-streaming/whisper-multilingual-streamingto confirm the page displays properlyspeechModel: "whisper-streaming",languageDetection: true) match the actual SDK APIRecommended test plan: Run the local docs server and visually inspect the hidden page to ensure all MDX components (Accordion, Tabs, Notes, code blocks) render correctly.
Notes
fern checkpassed for docs validation. Pre-existing errors inopenapi.ymlare unrelated to this change.Link to Devin run: https://app.devin.ai/sessions/0c82ef0f73db4904b5d3b5cde11e1e31
Requested by: Ryan Seams (@ryanseams)