#TTS
17 related articles
Kitten-TTS 2 Open-Sourced: A 1.58-Bit TTS That Runs in Real Time on CPU with Voice Cloning
KittenML open-sources Kitten-TTS 2, the world's first 1.58-bit TTS with 1.7B ternary-weight parameters, real-time CPU speech synthesis, 5-second zero-shot voice cloning, 20+ languages, and emotion/accent control—a new low-cost self-hosted TTS option.
Mistral Releases Voxtral 3: Speech-to-Text, TTS, and a Voice Agent SDK
Mistral AI releases Voxtral 3, featuring 3 transcription models, 1 TTS model, and a LiveKit-based Voice Agent SDK. Voxtral Small Transcribe 3 scores 2.1% AA-WER, ranking third on Artificial Analysis.
Voice AI Beginner's Guide: TTS, Voice Cloning, and Hands-On with ElevenLabs
A developer's guide to voice AI: the difference between traditional and neural TTS, the four-step voice cloning process, and ElevenLabs examples in Python/Node.js/cURL for text-to-speech and voice chatbots.
Generating Realistic Exam Listening with TTS: Multi-Voice, Pauses, and Timestamps Explained
Build exam listening practice from scratch: use ElevenLabs TTS for multi-voice speech, concatenate with ffmpeg, extract precise timestamps, and sync line-by-line highlighting.
Local Voice Assistant on an 8GB GPU: Making the LLM Yield to TTS to Eliminate Stuttering
A developer shares lessons from running a local voice assistant on an RTX 4060 Laptop with 8GB VRAM: letting the LLM pause after each sentence, letting TTS synthesize at full speed, then resuming cut first-audio latency from 3.9s to 2.3s and stuttering from an average of 2.84s to 0.09s, with a detailed analysis of GPU resource contention and VRAM optimization strategies.
Handling Edge Cases in TTS Applications: Long Text, Emoji, and Rate Limiting
How to handle common edge cases in TTS applications: long text chunking and pause stitching, emoji and Markdown cleaning, 429 rate-limit exponential backoff retries, SSML annotation for rare words in voice cloning, and production health monitoring, with Python and curl examples.
Adding Voiceovers to Faceless Videos with a TTS API: A Hands-On Guide to Multilingual Endpoints
Learn how to use the Multilingual Text-to-Speech API to quickly add multilingual voiceovers to faceless videos. Supports 9 languages, 54 voices, with curl examples and RapidAPI free tier tips.
Add AI Voice Narration to Your WordPress Site with ElevenLabs
Step-by-step guide to adding AI voice narration to WordPress using ElevenLabs TTS and voice cloning API — includes plugin code, shortcode, click-to-listen button, and caching tips.
Latency in Voice AI: Why It Matters and How to Optimize It
Deep dive into voice AI latency: how it forms, why it hurts UX, and practical strategies—streaming TTS, caching, prefetching, local models, and network optimization—with ElevenLabs code examples.
Building Free Urdu AI Voice with Gemini TTS: Three Bugs We Learned the Hard Way
A Pakistani team built free Urdu TTS with Gemini, hitting three real bugs: instructions read aloud, WAV double-header noise, and WhatsApp audio truncation. Here's how they fixed each one.
Google Launches Gemini 3.8 TTS: From Preset Voices to a Fully Customizable Voice Studio
Google's Gemini 3.8 Flash TTS and Flash-Lite TTS models bring generative voice design, line-by-line direction, two-speaker dialogue, and SynthID watermarking across 100+ languages.
Voxtral TTS Released: A New Frontier in Open-Weight Speech Synthesis
Mistral releases Voxtral TTS, an open-weight speech synthesis model supporting 9 languages, natural emotional expression, ultra-low latency, and easy voice adaptation for local deployment.
Product ReviewsXiaomi mimo-v2-tts Pitfall Report: Three Major Bugs — Contradictory Docs, Misread Tags, and Audio Cross-Contamination
A deep dive into three critical bugs in Xiaomi's mimo-v2-tts: contradictory docs, control tags read aloud, and backend audio cross-contamination with privacy risks.
TutorialsXcode MCP + Claude Sonnet 4 in Action: Building a Mac TTS App with Zero Hand-Written Code
A detailed walkthrough of using Xcode MCP with Claude Sonnet 4 to build a Mac local TTS app entirely through AI-generated code, covering setup, design guidelines, and results.
Product ReviewsInworld Realtime TTS-2: A Deep Dive into Full-Stack Real-Time Voice AI Infrastructure
Deep dive into Inworld's Realtime TTS-2 full-stack voice AI platform, covering its #1-ranked TTS engine, Speech-to-Speech processing, LLM routing, and applications in voice agents and AI companions.
TutorialsMoS-TTS-Nano Deployment Guide: Ultra-Lightweight 0.1B TTS Model That Runs on CPU
Battle-tested MoS-TTS-Nano local deployment guide. 0.1B ultra-lightweight TTS model runs on quad-core CPU without GPU. Covers Conda setup, pynini installation fixes, model download, and Gradio WebUI.
Product ReviewsBailing: Open-Source Voice Assistant with 800ms Low Latency, Rivaling GPT-4o Conversation Experience
Bailing is an open-source voice assistant using ASR+LLM+TTS architecture with DeepSeek R1 integration, achieving 800ms end-to-end latency with barge-in support, running smoothly on Mac and low-spec devices.