Zyphra releases ZONOS3-Mini, open-source TTS with 100M parameters
The fetched page is only a cookie notice, so license, languages, and availability are not confirmed.
Stories per day · 30 days
2 RSS
Relatedvoice-agents4mistral3open-source3speech-to-text3voxtral3low-resource2open-weights2voice-cloning2apache-2.01assemblyai1audio8-tts1basque1cpu-inference1cross-lingual1diffusion1drama-31edge01fish-audio1
29 stories, newest first · one card per story
Stories tagged #text-to-speech
WaveGen generates speech waveforms end to end without external codecs
Scaled from 0.1B to 0.6B parameters, it reports a 1.47 word error rate and 0.75 similarity on Seed-en.
ConwayResearch publishes Underdog Woof, a 40.6 MB English TTS model
The model card claims 1.42% word error rate for Mira and CPU-only synthesis with numpy.
Ruby-OPD enhances pronunciation controllability for flow-matching TTS
Ruby-OPD framework improves pronunciation accuracy on raw orthographic text for Japanese flow-matching TTS.
Edge0 releases Audio8-TTS-Realistic, a 0.6B voice-cloning TTS model
The fetched page only names the 0.6B model; license, weights, and benchmarks are not in the text.
5
AssemblyAI ships TTS-1 API at $15 per 1M characters
The hosted model runs only in US and EU clouds, with six languages, instant cloning and no open weights.
1
First open Basque speech language model built on LLaMA-Omni
Fine-tuning a Latxa backbone on translated, synthesized VoiceAssistant-400K data scored 3.86/5 content quality and 9.94% WER.
Gradium open-sources Phonon, a 31M-parameter on-device TTS model
The release is licensed under Apache 2.0; the article body was not available beyond the title.
4
Mistral AI releases Voxtral 3 speech models and voice SDK
The captured page only preserves the release title; sizes, benchmarks, and availability are not stated.
RubatoCodec adds budgeted adaptive speech tokens and streaming decode
Code and weights are public; adaptive allocation beat fixed-rate coding on reconstruction and intelligibility at low event rates.
Mistral launches Voxtral 3 real-time voice agent stack
The stack pairs transcription, speech synthesis and a LiveKit SDK, priced from $0.0035 per minute.
Mistral releases Voxtral 3 speech models and voice agent SDK
The family adds multilingual transcription and speech synthesis, offered on an EU-hosted API or for self-hosting.
SEAM expands TTS vocabularies without paired audio fine-tuning
The method matches or approaches baselines with up to four times less data across three languages and two architectures.
Fish Audio Releases Drama 3, a 35B Open-Weight MoE Text-to-Speech Model
Fish Audio released Drama 3, a 35B open-weight mixture-of-experts text-to-speech model.
2
Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model
Paradee distills Kokoro-82M into an 8M single-voice TTS model scoring 4.41 UTMOS.
AI music maker Suno now generates spoken words
Suno's Speech beta generates spoken voiceovers, with optional background music, for tracks up to eight minutes.
2
Microsoft AI releases new transcription and text-to-speech models for voice agents
Microsoft released MAI-Transcribe-2-Streaming and two MAI-Voice text-to-speech models for low-latency voice agents.
canberkkkkkk/ema-lightning — new model trending #30 on Hugging Face
EMA Lightning is an 8.6M-parameter Apache-2.0 Turkish TTS model reporting 0.92% WER on Freya-TR-Eval.
4
Open TTS Leaderboard: Scalable Evaluation for Multilingual Text-to-Speech and Voice Cloning
Hugging Face announces an Open TTS Leaderboard for multilingual speech and voice-cloning evaluation.
Muslim: A Deployed Arabic Voice AI Platform for Grounded Islamic Knowledge
Muslim is a production Arabic voice AI for sourced Islamic knowledge, releasing a 6B router and TTS model.
Twenty minutes with the CEO of ElevenLabs, now reportedly valued at $22 billion
ElevenLabs CEO says the voice-AI firm is at $600 million ARR and a reported $22 billion valuation.
1
Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning
Accent Analogy Guidance raises cross-lingual TTS speaker similarity at equal accent across several open models.
Google's new Flash TTS models let you design AI voices from scratch using text descriptions
Google released Gemini 3.8 Flash TTS and Flash-Lite TTS for designed, cloned, and multilingual synthetic voices.
Gemini 3.8 TTS Playground
Google released Gemini 3.8 Flash TTS models; Simon Willison published a bring-your-own-key playground.