Speech and audio
Speech recognition, synthesis, diarisation, music and general audio — the models themselves and the libraries that wrap them closely. A voice agent that merely calls one belongs in an application category.
84 in this category
NARROW BY WHAT THIS CATEGORY ASKS
LICENCE · 14 NOT READ
INPUT MODALITIES · 35 NOT READ
OUTPUT MODALITIES · 35 NOT READ
PRODUCTUSED BYSTARSDOWNLOADS 30D
Ggpt-sovits1 min voice data can also be used to train a good TTS model! (few shot voice cloning)61,709
chatttsA generative speech model for daily dialogue.39,828
voxcpmVoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning36,964Mmockingbird🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time36,909
handyA free, open source, and extensible speech-to-text application that works completely offline.31,408
faster-whisperFaster Whisper transcription with CTranslate225,503WwhisperxWhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)23,995Iindex-ttsAn Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System23,907
FunASRMulti-lingual large voice generation model, providing inference, training and deployment full-stack ability.23,723
voicestudioVoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.22,684
funasrOpen-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.20,458
diaA TTS model capable of generating ultra-realistic dialogue in one pass.19,398
kaldikaldi-asr/kaldi is the official location of the Kaldi project.15,481
vosk-apiOffline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node15,141
sherpa-onnxSpeech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android14,733
voice-proGradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isola12,880Eedge-ttsUse Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key11,920
speechbrainA PyTorch-based Speech Toolkit11,817WwhisperlivekitReal-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.11,077
moonshineVery low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces11,057
amphionAmphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, 10,287RrealtimesttA robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.10,126
espnetEnd-to-End Speech Processing Toolkit9,955
sensevoiceOpen-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.9,346Sspeech_recognitionSpeech recognition module for Python, supporting several engines and APIs, online and offline.8,988VvoicecraftZero-Shot Speech Editing and Text-to-Speech in the Wild8,577EemotivoiceEmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine8,524Aasrt_speechrecognitionA Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统8,386
mlx-audioA text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.7,924
espeak-ngeSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.6,826
annyang💬 Speech recognition for your site6,816
wav2letterFacebook AI Research's Automatic Speech Recognition Toolkit6,437
odsODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.6,397
argmax-oss-swiftOn-device Speech AI for Apple Silicon6,375Ssilero-modelsSilero Models: pre-trained text-to-speech models made embarrassingly simple6,098AabogenGenerate audiobooks from EPUBs, PDFs and text with synchronized captions.5,980Wwhisper-diarizationAutomatic Speech Recognition with Speaker Diarization based on OpenAI Whisper5,645
dograhOpen source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support.5,634
piper1-gplFast and local neural text-to-speech engine5,539Kkokoro-fastapiDockerized OpenAI-compatible wrapper for Kokoro-82M text-to-speech w/multiplatform CPU, AMD, NVIDIA GPU PyTorch; multi-speaker, clone-tuning, caption timestamps, SSML, optional readalong web UI5,432
smartsub视频转字幕、字幕翻译、AI 配音与声音克隆、字幕烧录——免费开源的一站式桌面工具。基于 Whisper / FunASR 等本地模型离线语音转文字，批量处理 + 全平台 GPU 加速，跨 Windows / macOS / Linux。Free, open-source desktop app to generate, translate, dub & burn video subtitles —5,111
porcupineOn-device wake word detection powered by deep learning4,935DdiffsingerDiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code4,858SsttVoice Recognition to Text Tool / 一个离线运行的本地音视频转字幕工具，输出json、srt字幕、纯文字格式4,786
whisperspeechAn Open Source text-to-speech system built by inverting Whisper.4,647
fastrtcThe python library for real-time communication4,623
pocketsphinxA small speech recognizer4,342
generative-media-skillsMulti-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI). High-quality image, video, and audio generation powered by muapi.ai.4,265
whisperliveA nearly-live implementation of OpenAI's Whisper.4,261RrealtimettsConverts text to speech in realtime4,026
applioA simple, high-quality voice conversion tool focused on ease of use and performance.3,706
whisper_streamingWhisper realtime streaming for long speech-to-text transcription and translation3,671
whisper-asr-webserviceOpenAI Whisper ASR Webservice API3,334
tts-webuiA single Gradio + React WebUI with extensions for ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, StyleTTS2, MAGNet, Au3,259
misottsMiso TTS is an 8 billion, highly emotive text-to-speech model3,238Wwhisper-standalone-winWhisper & Faster-Whisper standalone executables for those who don't want to bother with Python. 3,177Gghost-pepper100% private on-device voice models for speech-to-text and meeting transcription on macOS3,161
willowOpen source, local, and self-hosted Amazon Echo/Google Home competitive Voice Assistant alternative3,105
elevenlabs-pythonThe official Python SDK for the ElevenLabs API.3,093WwhishperTranscribe any audio to text, translate and edit subtitles 100% locally with a web UI. Powered by whisper models!3,071
delayed-streams-modelingKyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.3,021
whisper-timestampedMultilingual Automatic Speech Recognition with word-level timestamps and confidence2,844
fluidaudioFrontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source. 2,758
vieneu-ttsVietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 24kHz audio quality • Chuyển văn bản thành giọng nói tiếng Việt • Text to speech tiếng Việt • TTS tiếng Việt2,547Ppyttsx3Offline Text To Speech synthesis for python2,531
qwen-audio-agentA realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents2,413
ims-toucanControllable and fast Text-to-Speech for over 7000 languages!2,208
fireredasrOpen-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recogn1,983Nnerd-dictationSimple, hackable offline speech to text - using the VOSK-API.1,914
transcribe.cppggml speech-to-text inference for 16+ model families1,910Kkokoro-ttsA CLI text-to-speech tool using the Kokoro model, supporting multiple languages, voices (with blending), and various input formats including EPUB books and PDF documents.1,853
typewhisper-macLocal speech-to-text for macOS on-device AI, fully private, optional cloud1,781Vvoxtral.cPure C inference of Mistral Voxtral Realtime 4B speech to text model1,747Aauto-synced-translated-dubsAutomatically translates the text of a video based on a subtitle file, and then uses AI voice services to create a new dubbed & translated audio track where the speech is synced using the subtitle's t1,746SsopranoSoprano: Instant, Ultra-Realistic Text-to-Speech1,585
minimax-mcpOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.1,577Vvibevoice-comfyuiA comprehensive ComfyUI integration for Microsoft's VibeVoice text-to-speech model, enabling high-quality single and multi-speaker voice synthesis directly within your ComfyUI workflows.1,560Ffaster-qwen3-ttsReal-time text-to-speech with Qwen3-TTS1,346
airunnerOffline inference engine for art, real-time voice conversations, LLM powered chatbots and automated workflows1,314
kubeaiAI Inference Operator for Kubernetes. The easiest way to serve ML models in production. Supports VLMs, LLMs, embeddings, and speech-to-text.1,258
vuiVui Nano — a small, context-aware text-to-speech model trained on real conversations. 219M active params (305M total), Apache 2.0, voice cloning, streaming, runs on CPU (dependency-free C build). Ship760
ai-faceless-video-generatorGenerate a video script, voice and a talking face completely with AI497
IBM GraniteIBM Granite, open model family for enterprise273
Reka AINatively multimodal models for video, image, audio and textSORTED BY ONE STATED COLUMN · USED BY = LISTED PRODUCTS DEPENDING ON IT, IN THIS DIRECTORY — NOT A POPULARITY FIGURE · NO OVERALL SCORE AND NO RANK COLUMN, BECAUSE BLENDING ADOPTION, STARS AND DOWNLOADS NEEDS WEIGHTS, AND WEIGHTS ARE AN OPINION PRESENTED AS ARITHMETIC
Cite this page
The count and its date sit inside the citation, because “Speech and audio” without a date is a claim that quietly goes wrong as the category fills.
infratoapp, “Speech and audio — Model / Foundation”, read 28 October 2026. 84 listed products. https://www.infratoapp.com/layers/models/speech-audio
No overall score, and no rank column
Blending adoption, stars and downloads needs weights, and weights are an opinion presented as arithmetic — so this table sorts by one stated column at a time and shows which. This view holds no billing column and joins no billing table: a sponsor cannot appear higher, and the signals meter is a row’s own confidence, never a score you can sort on.
Frequently asked
What is in the Speech and audio category?
84 products in the Model / Foundation layer of the AI stack. Speech recognition, synthesis, diarisation, music and general audio — the models themselves and the libraries that wrap them closely. A voice agent that merely calls one belongs in an application category. Listed members include gpt-sovits, chattts and voxcpm. Every fact on each listing carries the page it was read from and the date it was read.
How are Speech and audio compared here?
By the 10 attributes this category declares, asked of every member and answered only where a source states it. A product with no answer on record shows a gap rather than a guess, and no blended score is published — weights would be an opinion presented as arithmetic.
gpt-sovits or chattts?
Both are listed under Speech and audio. We publish no verdict between them — we hold no benchmark that would support one. What we do hold is the same attribute sheet for each, side by side with the source behind every value, at /compare/chattts-vs-gpt-sovits.
What does a blank mean on a speech and audio row?
That nobody has told us, not that the answer is no. A hollow ring is "no answer on record", which is a different state from a recorded no — and the two look different on purpose. A listing with a blank has not failed the question; it has not been read for it.
How often are speech and audio figures re-read?
Every value carries the date it was read and a link to the page it came from. Prices move fastest and are re-read most often; an attribute read weeks ago says so rather than presenting itself as current. Anything past 21 days is hidden rather than shown stale.
Is this every speech and audio there is?
No. This is 84 we have read and can cite. A directory that claimed completeness would be making a promise it cannot keep, so the page states its own count instead and says when a category is too thin to shortlist from.
Can a vendor pay to rank higher here?
No. Nothing on this page can be bought: a sponsor cannot enter a table, reorder a row or change a mark, and there is no ranked position for sale. How the site is paid for, and the line each source of money does not cross, is set out under money and independence at /our-data#sec5.