>>> [!note] Migrated issue <!-- Drupal.org comment --> <!-- Migrated from issue #3572951. --> Reported by: [jibla](https://www.drupal.org/user/1013184) Related to !31 >>> <p>[Tracker]<br> <strong>Update Summary: </strong>New - TTS via dedicated Gemini TTS models<br> <strong>Check-in Date: </strong>02/11/2026<br> <strong>Additional Collaborators: </strong><br> <em>Metadata is used by the <a href="https://www.drupalstarforge.ai/" title="AI Tracker">AI Tracker.</a> Docs and additional fields <a href="https://www.drupalstarforge.ai/ai-dashboard/docs" title="AI Issue Tracker Documentation">here</a>.</em><br> [/Tracker]</p> <h3 id="summary-problem-motivation">Problem/Motivation</h3> <p>Gemini now offers dedicated TTS models (<code>gemini-2.5-flash-preview-tts</code>, <code>gemini-2.5-pro-preview-tts</code>) supporting 30+ prebuilt voices and 100+ languages. The <code>google-gemini-php/client</code> library has supported TTS since v2.3.0 (our composer requirement of <code>^2.5</code> already covers this).</p> <p>The OpenAI provider already implements <code>TextToSpeechInterface</code>. We should reach parity.</p> <h3 id="summary-proposed-resolution">Proposed resolution</h3> <ul> <li>Implement <code>TextToSpeechInterface</code> in GeminiProvider</li> <li>Add <code>text_to_speech</code> to <code>getSupportedOperationTypes()</code></li> <li>Use <code>generateContent</code> with <code>responseModalities: ["AUDIO"]</code> and <code>SpeechConfig</code> for voice selection</li> <li>Map Gemini's PCM audio output (24kHz) to AI module's <code>AudioFile</code> objects in <code>TextToSpeechOutput</code></li> <li>Add TTS configuration section to <code>definitions/api_defaults.yml</code> (voice selection)</li> <li>Add model filtering in <code>getConfiguredModels()</code> for TTS models</li> <li>Update <code>ai_provider_info.yml</code> with <code>text_to_speech</code></li> <li>Add tests</li> </ul> <p><strong>References:</strong></p> <ul> <li><a href="https://ai.google.dev/gemini-api/docs/speech-generation">Gemini TTS documentation</a></li> <li><a href="https://github.com/google-gemini-php/client">google-gemini-php/client</a> (TTS since v2.3.0)</li> </ul> <h3 id="summary-remaining-tasks">Target date or deadline</h3> <p>Before stable release.</p> <h3 id="summary-remaining-tasks">Remaining tasks</h3> <ul> <li>Implement <code>TextToSpeechInterface</code></li> <li>Add voice configuration to api_defaults.yml</li> <li>Handle PCM to WAV/MP3 conversion if needed by AI module</li> <li>Add model filtering for TTS operation type</li> <li>Write tests</li> <li>phpcs clean</li> </ul> <h3 id="summary-ai-usage">AI usage (if applicable)</h3> <p>[x] AI Assisted Issue<br> This issue was generated with AI assistance, but was reviewed and refined by the creator.</p> <p>[ ] AI Assisted Code</p> <p>[ ] AI Generated Code</p> <p>[ ] Vibe Coded</p>