#text-to-speech
Text-To-Speech: 12 AI articles covering text-to-speech news, analysis, and research
Articles
A Closer Look at Phonon TTS: Launching High-Quality On-Deviceβ9
Phonon TTS is a 31M-parameter on-device text-to-speech model for ExecuTorch and WebGPU, delivering high-quality local speech synthesis that tops its size class ...
Deepgram Acquires Pipecat Maker Daily to Strengthen Voice AIβ9
Deepgram acquires Daily, creator of open-source voice AI framework Pipecat, to strengthen real-time voice infrastructure. Pipecat will remain open-source.
Mistral AI Launches Voxtral 3: Speech-to-Text, TTS, and a Voiceβ8
Mistral AI launches Voxtral 3: three speech-to-text models, a TTS model, and a LiveKit-based voice agent SDK for building end-to-end voice agents.
Fish Audio Releases Drama 3: A 35B Open-Weight MoE Text-toβ8
Fish Audio releases Drama 3, a 35B open-weight MoE text-to-speech model with 3B active parameters, running on a single 48GB GPU for scripted dialogue and dubbin...
AI Music Maker Suno Now Generates Spoken Words with Its Newβ8
Suno launches a Speech feature that generates AI voiceovers with background music, expanding into text-to-speech for audiobooks, podcasts, and ads.
Twenty Minutes with ElevenLabs CEO Mati Staniszewski: Inside theβ9
ElevenLabs CEO Mati Staniszewski on building the $22B voice AI company, AI disclosure, competition, and why he prioritizes market share over margins.
India's Pocket FM Doubles Revenue Run Rate to $500M as AI Powersβ7
Pocket FM doubles its revenue run rate to $500M as AI now powers 93% of its catalog and 99% of new audio content, cutting production costs by 80x.
Gradium Launches Voice Design: Write a Prompt, Get a Brand Newβ8
Gradium Voice Design turns written descriptions into custom synthetic voices in secondsβno recording needed. Live on API and Studio with free tier access.
Gradium AI Launches New Default TTS Model: 81.0% Hard-Case Passβ7
Gradium AI launches a new default TTS model with an 81.0% hard-case pass rate, 216 ms time-to-first-audio, outperforming Cartesia and ElevenLabs.
Lowest-Latency Inference APIs for Voice and Realtime Agents: Aβ9
TTFT alone misleads voice AI latency benchmarks. This guide measures the full stackβSTT, LLM, TTS, and speech-to-speechβto reveal which inference APIs truly fee...
