Repository navigation
feat(voice): read aloud with Gemini TTS or macOS say, and pick the voice in Settings - #268
Merged
Merged
Conversation
…rovider's voices Gemini (its 30 prebuilt voices, PCM wrapped as WAV) and macOS say (the Mac's own voices, text on stdin) join OpenAI-compatible, ElevenLabs and Deepgram as text-to-speech providers. GET /voice/voices lists the voices a provider reads in; POST /voice/speak takes a voice to try. Podcast hosts use the same voices. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WkPdbtd7zvYMRWaRkLN2F6
…s list, and hear it Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WkPdbtd7zvYMRWaRkLN2F6
18 of 22 tasks
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Requested by Adeel · project thread
Description
Before: spoken answers and podcasts could be read by an OpenAI-compatible server, ElevenLabs or Deepgram, and the voice was a free-text id you had to look up yourself.
After: Google Gemini TTS (its 30 prebuilt voices) and macOS
say(the Mac's own voices, when Lens runs on a Mac itself) are also offered. Settings → AI assistant → Voice shows the provider's voices in a list (ElevenLabs from your account, Deepgram's Aura models,say -v ?, an OpenAI-compatible server's/audio/voiceswhen it has one, else OpenAI's own, Gemini's fixed list) with a Hear button that plays a sample before you keep it. Settings → Speech providers gets a Google Gemini block (address, model, key, Test). Podcast hosts use the same providers and voices.How:
speech.speak()dispatches per provider; Gemini's raw PCM is wrapped as WAV;saygets the text on stdin so nothing in it is read as an option. NewGET /voice/voices?provider=…;POST /voice/speaktakes an optionalvoice. New settingsspeech.gemini_base_url,gemini_model,gemini_api_key(sealed). StyleTTS2 (opt-in local service) follows in its own PR.Motivation and Context
Adeel asked for ElevenLabs, macOS
say, Gemini TTS and StyleTTS2 with voice selection.Types of changes
!in the title)Checklist:
make hookschecks it on commit).docs/accordingly.## UnreleasedinCHANGELOG.md.🤖 Generated with Claude Code
https://claude.ai/code/session_01WkPdbtd7zvYMRWaRkLN2F6