Implement ElevenLabs TTS

PromtEngineer / Verbi

A modular voice assistant application for experimenting with state-of-the-art transcription, response generation, and text-to-speech models. Supports OpenAI, Groq, Elevanlabs, CartesiaAI, and Deepgram APIs, plus local models via Ollama. Ideal for research and development in voice technology.

MIT License

123 stars 35 forks source link

Implement ElevenLabs TTS #4

Closed 3choff closed 4 weeks ago

3choff commented 1 month ago

ElevenLabs Text-to-Speech (TTS) Integration:

The voice assistant can now use the ElevenLabs TTS service for generating speech.
The voice ID for the ElevenLabs TTS service is set to "Paul J.", which closely resembles Jarvis's voice.
The output format is "mp3_22050_32" to ensure compatibility with the Free Tier of ElevenLabs's account.
The model "eleven_turbo_v2" provides a good balance of speed and audio quality.
The README has been updated with instructions and a link to the voice.

3choff commented 1 month ago

@PromtEngineer I just sent the PR. The voice sounds very similar to me. Let me know if any changes are required

PromtEngineer commented 1 month ago

@3choff I will have a look. thanks for another amazing contribution.

PromtEngineer commented 1 month ago

@3choff can you please update the example.env file with ELEVAN_LABS_API. This looks great.

3choff commented 1 month ago

@PromtEngineer Thanks, I updated the example.env