8000 Voice: Sarvam bulbul:v4-flash voices by AffanShaikhsurab · Pull Request #6 · AffanShaikhsurab/alina · GitHub
[go: up one dir, main page]

Skip to content

Voice: Sarvam bulbul:v4-flash voices - #6

Open
AffanShaikhsurab wants to merge 2 commits into
lifeos/v0.2.0-voicefrom
alina/sarvam-v4-flash
Open

AffanShaikhsurab wants to merge 2 commits into
lifeos/v0.2.0-voicefrom
alina/sarvam-v4-flash

Conversation

@AffanShaikhsurab
@AffanShaikhsurab AffanShaikhsurab commented Oct 16, 2026 •
Copy link
Copy Markdown
Owner

Why

Sarvam's newer bulbul:v4-flash model has expressive persona voices, but the voice picker only offered bulbul:v3 speakers.

What changed

  • The Sarvam voice list adds 24 English and English-Hindi bulbul:v4-flash personas after the v3 speakers.
  • Choosing a v4 persona sends model bulbul:v4-flash, because those voices exist only on that model. v3 speakers keep the connection or deployment model, as before.
  • Per Sarvam's docs, v4 Flash uses the same request and response format as v3.

How it was tested

Not run locally (small change). CI covers the adapter tests.

New user-facing copy

Voice labels such as 'Shubh · companion · English–Hindi (v4 Flash)'. They name the persona, its style and language so the long voice ids are readable in the picker, and they appear only in Sarvam's voice list.

Summary by CodeRabbit

  • New Features
    • Added 24 Sarvam voice options, with labels reflecting each persona’s name, style, and English or English–Hindi language.
    • Selecting one of these persona voices uses the corresponding speech synthesis model. Other voices continue to use the existing model selection behavior.

Lists English and English-Hindi bulbul:v4-flash personas after the bulbul:v3 speakers. A v4 persona id always selects the bulbul:v4-flash model, since it only exists there; v3 speakers keep the configured model.
@coderabbitai
coderabbitai Bot commented Oct 16, 2026 •
Copy link
Copy Markdown

Review in Change Stack →

Warning

Review limit reached

You've used all free OSS reviews for now. Wait for the free limit to reset to keep reviewing this public repository.

Next included review available in 36 minutes.

Check out review usage here.

View limit details

Limit details: You’ve used the included review currently available.

Learn how review limits work.

Review configuration:

⚙️ Run configuration
  • Configuration used: Repository: AffanShaikhsurab/alina/.coderabbit.yaml
  • Review profile: CHILL
  • Plan: Advanced
  • Run ID: eaae8f33-5567-4856-a83f-035f4cb47ab9
📥 Commits

Reviewing files that changed from the base of the PR and between 5fc1e5b and fbf5804.

⛔ Files ignored due to path filters: 1
  • pnpm-lock.yaml is excluded by !**/pnpm-lock.yaml
📒 Files selected for processing: 1
  • apps/mobile/package.json

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration
  • Configuration used: Repository: AffanShaikhsurab/alina/.coderabbit.yaml
  • Review profile: CHILL
  • Plan: Advanced
  • Run ID: c86f67b8-4b78-48a6-a6cb-8edef5c11a05
📥 Commits

Reviewing files that changed from the base of the PR and between f96df54 and 5fc1e5b.

📒 Files selected for processing: 1
  • packages/adapters/src/sarvam-voice.ts

Included review availability: This review used your included allowance. Your plan provides up to 1 included review per hour; 0 remain after this review.

📝 Walkthrough

The Sarvam voice catalog now includes 24 bulbul:v4-flash persona voices. Synthesis selects bulbul:v4-flash for matching persona IDs and retains the existing model fallback order for other IDs.

Changes: Sarvam persona voices

Layer / File(s) Summary
Persona catalog and synthesis routing
packages/adapters/src/sarvam-voice.ts
The catalog combines the existing speakers with 24 v4 Flash personas labeled by name, style, and language. Synthesis forces bulbul:v4-flash for matching persona IDs; other IDs use the request override, valid SARVAM_TTS_MODEL, then bulbul:v3.

Priority: ⬇️ Low

Estimated code review effort: 2 (Simple) | ~10 minutes

Change: Feature

Merge Risk: ⚪ Minimal · up to 5fc1e

The new personas are listed and routed to v4 Flash with their speaker IDs intact; no concrete user-facing failure or merge blocker is established.

Pre-merge checks: Passed 4 · Failed 1

Failed Failed checks: 1 warning

Check name Status Explanation Resolution
Docstring Coverage Warning Docstring coverage is 50.00% which is insufficient. The required threshold is 80.00%. Docstring coverage is scoped to functions touched by this diff. Analyzed 2 functions across 1 files. Write docstrings for the functions missing them to satisfy the coverage threshold.
Passed Passed checks: 4 passed
Check name Status Explanation
Description Check Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check Passed The title clearly identifies the main change: adding Sarvam bulbul:v4-flash voices.
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.
✨ Finishing Touches: 💡 2
📝 Generate docstrings: 💡
  • Commit to this branch
  • Create a new PR
🛠️ Fix failing CI checks: 💡
  • Commit to this branch
  • Create a new PR
🧪 Generate unit tests (beta)
  • Commit to this branch
  • Create a new PR
  • Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands.

Bump @expo/ui, expo, and expo-router to the SDK 57 patches expo install --check expects, and keep @better-auth/utils at 0.4.2 with core 1.7.7.

(cherry picked from commit f76b8a63dfa68b61dc8f69a546436fda9c3a6035)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants

0