Announcements we track
New releases
Models announced or first listed recently that are still waiting for an independent board we track — sorted newest first. Same corpus as the home “Newly tracked” strip.
Oct 22
C
Chariot-1-ASR Realtime
Chariot · Chariot's streaming speech-recognition model for Indian languages
API live
Oct 21
S
Simba 3.5
Speechify · Speechify's text-to-speech model that speaks 48 languages under a single model id, with every catalog voice and cloned voices usable in any of them
API live
Oct 20
U
Underdog Bark 3.0
Underdog · Underdog's small open English speech-to-text model, built to run on Macs and phones
open weights
Oct 20
1
Eleven Realtime
ElevenLabs · ElevenLabs' new class of speech-to-speech models for voice agents, which the lab says starts talking in about half a second
API live
Oct 20
H
FastH3 Omni
Hao AI Lab (UC San Diego) · Hao AI Lab's FastVideo team's 8-step reference-to-video model, distilled from MiniMax's MiniMax-H3: video with synchronized audio from a text prompt plus…
open weights
Oct 20
O
Naad v2
Oogam AI · Oogam AI's speech-to-text and text-to-speech models for 28 Indian languages (3 in beta), offered through the Oogam API
API live
Oct 20
G
Phonon
Gradium · Gradium's suite of on-device text-to-speech models under 50M parameters, built to run offline on phones, laptops, small boards and in the browser
open weights
Oct 20
K
Pocket TTS 4.0
Kyutai · Kyutai's Pocket TTS v4.0.0 release: six small English text-to-speech models with voice cloning, at 18.2M, 6.9M and 1.9M parameters, each with a…
open weights
Oct 20
M
Voxtral 3
Mistral · Mistral's new speech-to-text and text-to-speech models, with a voice agent SDK built on LiveKit and Pro Voice cloning from up to 30 minutes of audio
API live
Oct 19
I
Ming-3.0
Ant Ling (InclusionAI, Ant Group) · InclusionAI's open Ming-3.0 audio family: multilingual TTS with voice cloning, Chinese/English ASR with dialects, and native audio-language MoE models for…
open weights
Oct 15
I
Granite Switch 4.1
IBM · IBM's 8B and 30B Granite Switch models: one checkpoint that switches through control tokens between chat, a general Decision adapter, a Guardian safety adapter…
open weights
Oct 15
M
Jais 3
IFM (MBZUAI) with Inception42 · A family of six open, Arabic-native models for agentic work, 0.9B to 375B, built on IFM's K2 Horizon
API live · open weights
Oct 15
N
TYGER
NineNineSix · NineNineSix's open full-duplex voice model, with the TYGER S2S agent
open weights
Oct 15
O
GPT-Live-1.1
OpenAI · OpenAI's voice model update for Voice in ChatGPT, Codex and dots, with better accents and new voices in French, German, Hindi, Mexican Spanish, Korean and…
Tracking
Oct 14
X
Grok Voice 3.0
xAI · Speech-to-speech successor to Grok Voice 2.0, available in the API and Voice Agent Builder
API live
Oct 14
M
Mirelo SFX 2.0
Mirelo · Mirelo's video-to-sound model
API live
Oct 13
F
Drama 3
Fish Audio · Fish Audio's open-weight text-to-speech model
API live · open weights