Skip to content

Feature/google cloud tts - #1

Merged
codewithfourtix merged 2 commits into
mainfrom
feature/google-cloud-tts
Jun 17, 2026
Merged

codewithfourtix merged 2 commits into
mainfrom
feature/google-cloud-tts

Conversation

@codewithfourtix

Copy link
Copy Markdown
Owner

No description provided.

codewithfourtix and others added 2 commits June 17, 2026 11:35
- Drop unused OpenRouter/Kokoro TTS path (synthesizeSpeech + tts* config);
  Kokoro does not speak Urdu, so the bot only ever used Google TTS.
- Remove the unused Urdu->Hindi transliterator; keep only the speech-text
  cleanup helper and rename urdu-to-hindi.js -> speech-text.js.
- README: fix project structure, drop references to nonexistent test files.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Use the official Google Cloud Text-to-Speech API (ur-IN neural voice) as the
primary voice path when GOOGLE_TTS_API_KEY is set. It is production-grade with
no IP rate limits, unlike the free translate_tts endpoint.

The free Google Translate TTS remains as an automatic fallback: it is used when
no API key is configured, or whenever a Cloud TTS request fails, so voice
replies never break.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
@codewithfourtix
codewithfourtix merged commit af5bcda into main Jun 17, 2026
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.

1 participant