Documentation →
Discover how to use the latest Gemini text-to-speech (TTS) models through Firebase AI Logic. Learn how to generate low-latency, hyper-realistic audio, control emotions using inline audio tags, structure prompts with director's notes, and even orchestrate dynamic multi-character dialogues in a single prompt with multiSpeakerVoiceConfig—all protected by Firebase App Check and Firebase Authentication.
Chapters:
0:00 - Introduction
0:59 - Setting up getGenerativeModel
1:47- Configuring voices (voiceConfig)
3:00 - Demo
3:32 - Audio tags
4:14 - Prompt structuring
4:50 - Multi-Speaker
#Firebase #AI
Watch more Firebase Release Notes Deep Dive →
Subscribe to Firebase →
Speaker: Roger Martinez
Products Mentioned: Firebase
|
Join the GameDay crew as we take on a re...
Having trouble with two-way SMS in AWS E...
AWS Elemental Inference applies AI in pa...
Documentation → Discover how to use t...
Say goodbye to redundant constructor boi...
Live from FlutterCon USA in Orlando, And...
Challenger Center, a 2024 AWS Imagine Gr...
Lieber Institute for Brain Development, ...
本日は脱・AIスライドについてお話させて頂きました! ぜひご視聴ください! ...
I did a little experiment where I create...