Document HostedVoiceCloneConfig for pipecat and livekit plugins by serhatzx · Pull Request #26 · deepslate-labs/deepslate-docs

serhatzx · 2026-06-04T11:22:46Z

Summary by CodeRabbit

Documentation
- Updated the RealtimeModel configuration reference to document expanded tts_config support, including hosted voice cloning via HostedVoiceCloneConfig.
- Added a new documentation section covering required audio sample metadata (PCM bytes, sample rate, channels, reference transcript, synthesis mode) and usage guidance.
- Updated WebSocket protocol documentation for hosted voice cloning, including revised recommended clean speech duration for audio sample data.
- Added a “Voice Cloning” feature card highlighting hosted pre-cloned voices and on-the-fly cloning from raw audio samples.

coderabbitai · 2026-06-04T11:22:57Z

📝 Walkthrough

Walkthrough

This PR adds documentation for the new HostedVoiceCloneConfig feature across LiveKit and Pipecat integration guides, updates the WebSocket API reference specifications with revised audio duration requirements, and announces the voice cloning capability in feature cards.

Changes

Voice Cloning Configuration Documentation

Layer / File(s)	Summary
HostedVoiceCloneConfig in integration guides `livekit.mdx`, `pipecat.mdx`	The `RealtimeModel` tts_config type expands to include `HostedVoiceCloneConfig`. Both guides document the new config with parameter descriptions for PCM audio data, sample rate, channels, reference transcript, and synthesis mode, plus usage examples and implementation tips.
HostedVoiceCloneV1 API reference specification `api-reference/realtime.mdx`	WebSocket protocol documentation is updated to specify that clean speech audio samples should be 10–15 seconds in duration (reduced from 20–25 seconds) for the `voice_clone_v1` guidance and the `audio_data` field description.
Voice Cloning feature cards `livekit.mdx`, `pipecat.mdx`	Feature cards are added to both integration guides' feature grids, announcing voice cloning capabilities including both pre-cloned hosted voices and on-the-fly cloning from raw audio without external TTS credentials.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related PRs

deepslate-labs/deepslate-docs#23: Both PRs document the same hosted voice-cloning configuration, introducing the feature across integration guides with configuration fields and usage examples.

Suggested reviewers

Janrupf

Poem

🐰 A voice so fine, now cloned with care,
Raw audio samples drift through the air,
No external keys, just truth to tell,
Shorter samples sing—ten seconds ring—
Configuration whispers, the feature bells! 🎵

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The pull request title accurately describes the main change: documenting HostedVoiceCloneConfig support across pipecat and livekit plugins, which is reflected in all three modified documentation files.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Commit unit tests in branch serhat/sdk-29-update-sdk-docs-to-include-voice-clone-tts

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

mintlify · 2026-06-04T11:23:35Z

Preview deployment for your docs. Learn more about Mintlify Previews.

Project	Status	Preview	Updated (UTC)
Deepslate	🟢 Ready	View Preview	Jun 4, 2026, 11:24 AM

💡 Tip: Enable Workflows to automatically generate PRs for you.

coderabbitai

Actionable comments posted: 2

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@livekit.mdx`:
- Line 153: The documented duration for the HostedVoiceClone audio sample is
incorrect; update the `audio_data` field description (the table entry currently
saying "10 to 15 seconds of speech") to "20 to 25 seconds of speech" in both
places it appears (the occurrences around the HostedVoiceClone/audio_data
examples), and ensure any sample snippets or examples referencing "10 to 15
seconds" are changed to "20 to 25 seconds" so the docs match the upstream schema
and avoid untested example misconfiguration.

In `@pipecat.mdx`:
- Line 185: Update the documented required duration for the `audio_data`
clone-sample from "10 to 15 seconds" to "20 to 25 seconds" in both places where
it appears (the two entries describing `audio_data` in the clone-sample/hosted
clone schema) so the docs match the hosted clone schema; do not add any example
code snippets that are untested while making this text change.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

Push a commit to this branch (recommended)
Create a new PR with the fixes

ℹ️ Review info

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: 0b9681ff-5966-4824-81e8-6b8d0bb48232

📥 Commits

Reviewing files that changed from the base of the PR and between 3f735c8 and fa8fe74.

📒 Files selected for processing (2)

livekit.mdx
pipecat.mdx

…10-15 seconds

coderabbitai

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@api-reference/realtime.mdx`:
- Line 620: The documentation changes at lines 620 and 661 in
api-reference/realtime.mdx now specify "10 to 15 seconds" for
HostedVoiceCloneV1.audio_data, but the HostedVoiceCloneV1.audio_data field
definition in api-reference/realtime.proto still documents "20 to 25 seconds".
Resolve this contract mismatch by choosing one as the source of truth: either
update the protobuf schema specification for HostedVoiceCloneV1.audio_data in
api-reference/realtime.proto to "10 to 15 seconds" to match the documentation,
or revert the documentation changes at lines 620 and 661 back to "20 to 25
seconds" to match the proto specification. Ensure all references across both
files use the same duration range consistently.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

Push a commit to this branch (recommended)
Create a new PR with the fixes

ℹ️ Review info

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: 0b2a0305-fe16-4810-a9d6-79bddaa9a566

📥 Commits

Reviewing files that changed from the base of the PR and between fa8fe74 and 321317b.

📒 Files selected for processing (1)

api-reference/realtime.mdx

coderabbitai · 2026-06-16T00:06:45Z


    <Note>
-    Use 20 to 25 seconds of clean speech for `voice_clone_v1.audio_data`. In JSON, protobuf `bytes` fields are base64-encoded; binary protobuf clients send the raw audio bytes.
+    Use 10 to 15 seconds of clean speech for `voice_clone_v1.audio_data`. In JSON, protobuf `bytes` fields are base64-encoded; binary protobuf clients send the raw audio bytes.


⚠️ Potential issue | 🟠 Major | ⚡ Quick win

Align HostedVoiceCloneV1.audio_data duration with the protobuf contract.

Line 620 and Line 661 now document 10–15 seconds, but api-reference/realtime.proto for HostedVoiceCloneV1.audio_data still specifies 20–25 seconds. This creates a contract mismatch between API reference and schema for the same field.

Please make one source of truth and update the other side in the same change (either docs back to 20–25 or proto+related docs to 10–15 consistently).

Also applies to: 661-661

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@api-reference/realtime.mdx` at line 620, The documentation changes at lines 620 and 661 in api-reference/realtime.mdx now specify "10 to 15 seconds" for HostedVoiceCloneV1.audio_data, but the HostedVoiceCloneV1.audio_data field definition in api-reference/realtime.proto still documents "20 to 25 seconds". Resolve this contract mismatch by choosing one as the source of truth: either update the protobuf schema specification for HostedVoiceCloneV1.audio_data in api-reference/realtime.proto to "10 to 15 seconds" to match the documentation, or revert the documentation changes at lines 620 and 661 back to "20 to 25 seconds" to match the proto specification. Ensure all references across both files use the same duration range consistently.

Document HostedVoiceCloneConfig for pipecat and livekit plugins

fa8fe74

serhatzx requested a review from Jannek312 June 4, 2026 11:22

mintlify Bot deployed to staging June 4, 2026 11:24 View deployment

coderabbitai Bot reviewed Jun 4, 2026

View reviewed changes

Comment thread livekit.mdx

Comment thread pipecat.mdx

Update recommended audio duration for voice_clone_v1.audio_data to …

321317b

…10-15 seconds

mintlify Bot deployed to staging June 16, 2026 00:05 View deployment

coderabbitai Bot reviewed Jun 16, 2026

View reviewed changes

Navigation Menu

Uh oh!

Document HostedVoiceCloneConfig for pipecat and livekit plugins - #26

Document HostedVoiceCloneConfig for pipecat and livekit plugins#26
serhatzx wants to merge 2 commits into
mainfrom
serhat/sdk-29-update-sdk-docs-to-include-voice-clone-tts

serhatzx commented Jun 4, 2026 •

edited by coderabbitai Bot

Loading

Uh oh!

coderabbitai Bot commented Jun 4, 2026 •

edited

Loading

Walkthrough

Changes

Estimated code review effort

Possibly related PRs

Suggested reviewers

Poem

Uh oh!

mintlify Bot commented Jun 4, 2026 •

edited

Loading

Uh oh!

coderabbitai Bot left a comment

Uh oh!

Uh oh!

Uh oh!

coderabbitai Bot left a comment

Uh oh!

coderabbitai Bot Jun 16, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

serhatzx commented Jun 4, 2026 • edited by coderabbitai Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Uh oh!

coderabbitai Bot commented Jun 4, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Possibly related PRs

Suggested reviewers

Poem

Uh oh!

mintlify Bot commented Jun 4, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

coderabbitai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

coderabbitai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

coderabbitai Bot Jun 16, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

serhatzx commented Jun 4, 2026 •

edited by coderabbitai Bot

Loading

coderabbitai Bot commented Jun 4, 2026 •

edited

Loading

mintlify Bot commented Jun 4, 2026 •

edited

Loading