
Kimi-Audio
Kimi-Audio,这是一个开源音频基础模型,在音频理解、生成和对话方面表现出色。此存储库包含 Kimi-Audio 的官方实现、模型和评估工具包。 通用功能:处理语音识别(ASR)、音频问答(AQA)、音频字幕(AAC)、语音情感识别(SER)、声音事件/场景分类(SEC/ASC)和端到端语音对话等多种任务。 最先进的性能:在众多音频基准测试中取得 SOTA 结果(参见评估和技术报告)。

Speechify
Speechify is a popular text-to-speech app for Chrome, iOS, and Android.

Verbatik
Convert text into natural-sounding speech in over 142 languages and accents with Verbatik's AI-powered platform.

Speechify Studio - AI Voice Generator
Create engaging artificial intelligence (AI) voiceovers for any type of project: videos, ads, e-learning, audiobooks, dubbing, among others. Speechify AI Voice Generator, with its 200+ voices across m

Clueso
Fastest and easiest way to create stunning product videos and docs

Kits AI
Transform your voice with AI artist voices. Create and train your own AI voice model.

Weights GG
Create AI voice covers and images for free.

LilyFM
LilyFM是创新的AI应用,能将网页文章转化为播客。应用基于先进的AI技术,将用户待读的文章内容转化为生动的音频,提供深度分析和提炼关键要点,帮助用户更高效地获取知识。LilyFM逼真的AI语音支持多种语言,提供自然、富有表现力的朗读体验。用户基于Share Extension一键保存文章到播放队列,随时随地在通勤、健身或休息时收听。LilyFM让稍后阅读转变为稍后收听,让知识获取更加便捷和轻松

Luvvoice - Free Text to Speech
Free text-to-speech tool with 200+ voices.

VoiceDub
Generate AI voice covers for songs.

Dub AI
Translate and dub videos effortlessly.

TopMediai®
AI-powered online media tools for video, audio, and photos.

AIWritingPal 智写助手
AIWritingPal: AI-powered tool for writing improvement.

Deepdub
Dubbing and voice over localization at scale.

DavinciAI Toolkit
Empowering non-technical users with AI tools.

Luppa AI
Luppa is the all-in-one AI-powered content creation platform that helps businesses and creators effortlessly produce, manage, and grow their brand across all digital channels.

Pipio
Create professional videos using AI-generated actors and voices in minutes with Pipio.

Neoform AI
AI models for African dialects and bridging language barriers

Dubformer
AI Dubbing & localization for media industry

Voisi AI
Multi-AI toolkit for voice and language transformations.

ioAudio
Transforming text into natural audio summaries.

spatial speech translation
空间语音翻译:利用双耳可听设备进行跨空间翻译 🗣️ 空间语音翻译 CHI 2025 论文“空间语音翻译:利用双耳可听设备进行跨空间翻译”的官方仓库 Youtube 视频演示: 💡 功能 我们首先实现多说话人和干扰条件下的语音翻译。 我们的同步和富有表现力的语音翻译模型可以在 Apple 芯片上实时运行。 首先,语音翻译的双耳渲染可以保留从输入到翻译输出的空间提示。 📑 开源

Countless.dev
Compare and evaluate various AI models and their specifications.

Resemble
Generate synthetic voices that resemble real humans in seconds.
只显示前20页数据