Nari Qwen3-TTS and Qwen3-ASR
Fast, low-cost speech APIs built on Qwen3 voice models
Emerged finds new products worth a look, daily — what’s new today
FireRedAudio
One open 9B audio model for speech recognition, understanding, TTS and editing
Teams juggling separate ASR, TTS and audio-analysis models can test a single open-weight model that handles all of them.
FireRedTeam's FireRedAudio is a general audio language model built on a 9B LLM with separate continuous representations for understanding and generation. It covers speech recognition, audio reasoning, zero-shot voice cloning, voice design from text, speech editing, and analysis of recordings up to about an hour with timestamps. Reported scores include 82.0 on MMAU and 0.71 CER on AISHELL-1. Weights are on Hugging Face and ModelScope under Apache-2.0.
More like this
VoiceMem
Open streaming memory for real-time voice agents, split into facts and feelings
BetterWispr
Hold a key, speak, and the words land wherever the cursor is
CleanTake
Patch a ruined line of speech with the same moment from your other recorder
Sparrow-2
A turn-taking model that knows when a voice agent should speak
Aloud
A Mac menu-bar reader that speaks any text with the current word highlighted