[PR #41] [MERGED] ElevenLabs Text to Speech, audio_generator is outdated, I changed to updated docs #43

New issue

Closed

opened 2026-03-03 16:41:29 +03:00 by kerem · 0 comments

kerem commented

2026-03-03 16:41:29 +03:00

Owner

📋 Pull Request Information

Original PR: https://github.com/neural-maze/ava-whatsapp-agent-course/pull/41
Author: @Excergic
Created: 9/19/2025
Status: ✅ Merged
Merged: 10/20/2025
Merged by: @MichaelisTrofficus

Base: main ← Head: speech-contribution

📝 Commits (1)

561c8ca Updated elevenlabs text to speech code

📊 Changes

1 file changed (+7 additions, -6 deletions)

View changed files

📝 src/ai_companion/modules/speech/text_to_speech.py (+7 -6)

📄 Description

OLD METHOS NOW API HAS CHANGED

         audio_generator = self.client.generate(
              text=text,
             voice=Voice(
             voice_id=settings.ELEVENLABS_VOICE_ID,
             settings=VoiceSettings(stability=0.5, similarity_boost=0.5),
        ),
        model=settings.TTS_MODEL_NAME,
         )

.generate() is no longer supported

New Method Added

audio_generator = self.client.text_to_speech.convert(
voice_id=settings.ELEVENLABS_VOICE_ID,
text=text,
model_id=settings.TTS_MODEL_NAME,
voice_settings = VoiceSettings(
stability=0.5,
similarity_boost=0.5
)
)

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/neural-maze/ava-whatsapp-agent-course/pull/41 **Author:** [@Excergic](https://github.com/Excergic) **Created:** 9/19/2025 **Status:** ✅ Merged **Merged:** 10/20/2025 **Merged by:** [@MichaelisTrofficus](https://github.com/MichaelisTrofficus) **Base:** `main` ← **Head:** `speech-contribution` --- ### 📝 Commits (1) - [`561c8ca`](https://github.com/neural-maze/ava-whatsapp-agent-course/commit/561c8cabf3c70ad79b4bd7c20c2e090eb3f30be7) Updated elevenlabs text to speech code ### 📊 Changes **1 file changed** (+7 additions, -6 deletions) <details> <summary>View changed files</summary> 📝 `src/ai_companion/modules/speech/text_to_speech.py` (+7 -6) </details> ### 📄 Description # OLD METHOS NOW API HAS CHANGED audio_generator = self.client.generate( text=text, voice=Voice( voice_id=settings.ELEVENLABS_VOICE_ID, settings=VoiceSettings(stability=0.5, similarity_boost=0.5), ), model=settings.TTS_MODEL_NAME, ) .generate() is no longer supported # New Method Added audio_generator = self.client.text_to_speech.convert( voice_id=settings.ELEVENLABS_VOICE_ID, text=text, model_id=settings.TTS_MODEL_NAME, voice_settings = VoiceSettings( stability=0.5, similarity_boost=0.5 ) ) --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>