Speech: TTS and ASR
- Speech: TTS and ASRProject
C Inference for Qwen3-ASR Transcription Models
The antirez/qwen-asr repository provides C inference for the Qwen3-ASR 0.6B and 1.7B transcription models.
It offers a C-based option for running speech recognition models in applications such as transcription bots and voice-driven interfaces.
- Speech: TTS and ASRArticle
vLLM Adds Streaming Inputs and a Realtime WebSocket API
The vLLM blog describes support for streamable inputs and a Realtime WebSocket API for audio, video, robotics, and low-latency applications that process inputs incrementally.
Engineers building low-latency audio systems can review vLLM’s streaming interface and examples.
- Speech: TTS and ASRProject
Local Studio PR adds ROCm and speech support
A pull request for Local Studio describes ROCm support and TTS/STT call mode using ACE-Step and Whisper v3 Large. It also mentions image and video support.
Engineers can review the proposed speech and AMD GPU support in the pull request.
- Speech: TTS and ASRProject
Hugging Face Open-Source Speech-to-Speech Repository
Hugging Face’s speech-to-speech repository is for building voice agents with open-source models.
It gives engineers a starting point for building voice agents with open-source models.
- 9 months ago @TheTuringPost
VoxCPM: tokenizer-free text-to-speech system
VoxCPM is a tokenizer-free TTS system built on the MiniCPM-4 backbone, using an end-to-end diffusion-autoregressive architecture. The post describes zero-shot voice cloning and expressive speech generation.
Engineers exploring TTS can assess an approach that generates continuous speech representations without discrete tokens.
vLLM adds support for Qwen3-ASR
vLLM has day-one support for Qwen3-ASR. The linked usage guide covers running the model with vLLM.
The guide gives engineers a starting point for serving Qwen3-ASR with vLLM.
- 9 months ago @JustinLin610
Qwen3-TTS announced as open source
The post announces that Qwen3-TTS is being open-sourced and mentions voice cloning and voice design. It does not include a repository or other link.
Engineers evaluating self-hosted TTS may want to investigate the model and its voice features.
- Speech: TTS and ASRModel
Step Audio R1.1 for Real-Time Speaking Dialogue
The post describes Step Audio R1.1 as a real-time, interactive speaking dialogue model under Apache 2.0. It claims the model can think while speaking and uses a dual-brain architecture for low latency.
Engineers can inspect the model page and evaluate its license and architecture claims for speech applications.
- 10 months ago @kyutai_labs
Pocket TTS: 100M-Parameter TTS for Laptops
Kyutai Labs introduces Pocket TTS, a 100M-parameter text-to-speech model that the post says supports voice cloning and runs on a laptop without a GPU. The post describes it as open-source.
Engineers can evaluate a self-hostable TTS model designed to run without a GPU.
- Speech: TTS and ASRArticle
LEMAS releases a 150K-hour multilingual speech dataset and models
LEMAS describes a 150K-hour multilingual audio suite and generative speech models. The post says the dataset covers 10 languages with word-level timestamps and names LEMAS-TTS and LEMAS-Edit.
Engineers can explore speech data and models for multilingual TTS and speech editing.
- Speech: TTS and ASRProject
Meta releases Omnilingual ASR for 1,600+ languages
Meta’s Omnilingual ASR is an open-source speech recognition model suite and dataset for more than 1,600 languages, including 500 described as previously unsupported.
Engineers can explore an open-source ASR system aimed at broad multilingual coverage.
- Speech: TTS and ASRProject
Step-Audio-EditX for Prompt-Based Audio Editing
StepFun says Step-Audio-EditX is a 3B-parameter model for audio editing, zero-shot multilingual TTS, and prompt-based control of emotion, speaking style, and vocal elements such as breaths and laughs. The post says it supports single-GPU deployment and uses Apache 2.0.
Engineers can evaluate a single-model approach to speech generation and iterative audio editing.
- Speech: TTS and ASRArticle
Inworld TTS 1 Max leads the Artificial Analysis Speech Arena
Artificial Analysis reports that Inworld TTS 1 Max leads its Speech Arena leaderboard, where users compare generated speech and choose their preferred output without seeing the model names. Inworld says TTS Max costs $10 per million characters.
The leaderboard describes a human-preference evaluation across four real-world speech categories.
- 1 year ago @ArtificialAnlys
Inworld TTS 1 Max leads the Artificial Analysis Speech Arena
The post reports that Inworld TTS 1 Max leads the Speech Arena leaderboard, which ranks TTS models through blind human comparisons. It describes both Inworld models’ 12-language support, short-audio voice cloning, and voice tags.
The comparison and feature details may help engineers assess TTS options.
- Speech: TTS and ASRProject
LongCat-Audio-Codec for Speech LLMs
Meituan open-sourced an audio tokenizer and detokenizer optimized for Speech LLMs. The post describes parallel semantic and acoustic tokens at 16.7 Hz, low-bitrate encoding, and a low-latency streaming decoder.
Engineers can evaluate its audio tokenization and streaming decoder for Speech LLM applications.
- 1 year ago @jiqizhixin
DiaMoE-TTS uses IPA and MoE for dialect speech synthesis
DiaMoE-TTS is an IPA-based dialect TTS framework with a dialect-aware Mixture-of-Experts and LoRA and Conditioning Adapters for adaptation. The post reports zero-shot synthesis on unseen dialects, including Peking Opera, with a few hours of data.
Its phonetic representation and adaptation approach may help engineers build TTS systems for dialects with limited data.
- 1 year ago @ArtificialAnlys
Gemini 2.5 Native Audio Thinking on Big Bench Audio
Artificial Analysis reports that Gemini 2.5 Native Audio Thinking scored 92% on its Big Bench Audio benchmark, which uses 1,000 audio questions adapted from Big Bench Hard. It reports 3.87 seconds average time to first token for the thinking model and 0.63 seconds for its non-thinking equivalent.
The results offer a reasoning benchmark and latency comparison for speech-to-speech models.
- 1 year ago @jiqizhixin
FireRedChat: Open-Source Full-Duplex Voice Interaction
FireRedChat is a pluggable voice interaction system with cascaded and semi-cascaded implementations. The post says it supports interruption handling, endpoint detection, real-time responses, emotion perception, and expressive speech synthesis.
Engineers can evaluate its architecture and voice interaction features for conversational assistants.
- Speech: TTS and ASRProject
Qwen3-Omni open-sources multimodal models with speech I/O
Qwen says it has open-sourced three Qwen3-Omni models for instruction following, reasoning, and captioning. The model combines text, image, audio, and video, with speech input and output.
Engineers can explore an open-source model that handles speech alongside other modalities.
- 1 year ago @jiqizhixin
Mini-Omni-Reasoner interleaves reasoning and speech
Mini-Omni-Reasoner uses a hierarchical Thinker–Talker architecture to interleave silent reasoning with spoken tokens. The post reports a new Spoken-Math-Problems-3M dataset and gains in arithmetic reasoning and contextual understanding.
The approach and reported results may inform designs for speech models that reason while speaking.
