Voice cloning

ZONOS2

By Zyphra AI

ZONOS2 is Zyphra’s open-source real-time text-to-speech model with MoE architecture, high-fidelity zero-shot voice cloning, and multilingual expressive speech generation.

NewMultimodal

Released 26d ago

🎧Audio translation 🔊Text to speech 🗣️Voice cloning 🗒Transcription

Gemini 3.5 Live Translate

By Google DeepMind

Gemini Audio is Google DeepMind’s closed-source native audio model family for low-latency live dialogue, controllable speech generation, audio understanding, and voice-first applications.

NewAudio

Released 29d ago

🔊Text to speech 🗣️Voice cloning 🎙️Voiceovers 🗣Dialogue generation

Higgs Audio v3 TTS

By Boson AI

Higgs Audio v3 TTS is Boson AI’s text-to-speech model for expressive conversational voice agents across 100+ languages with zero-shot voice cloning and inline speech controls.

NewAudio

Released 1mo ago

🔊Text to speech 🗣️Voice cloning 🎙️Voiceovers 🗣Dialogue generation

Miso TTS 8B

By Miso Labs

MisoTTS is Miso Labs’ open-weight 8B text-and-audio-conditioned speech generation model for expressive, context-aware, emotive TTS and dialogue voice output.

NewAudio

Released 1mo ago

MAI Voice 2 Flash

By Microsoft

MAI-Voice-2-Flash is Microsoft AI’s upcoming lower-cost, ultra-efficient variant of MAI-Voice-2 for speech generation.

NewMultimodal

Released 1mo ago

🔊Text to speech 🗣️Voice cloning 🎙️Voiceovers 🎧Audiobooks

MAI Voice 2

By Microsoft

MAI-Voice-2 is Microsoft AI’s speech generation model for natural-sounding voice output across 15 languages with short-sample voice adaptation.

NewMultimodal

Released 1mo ago

Phonon

By Gradium

Phonon is Gradium’s private-beta 100M-parameter on-device text-to-speech model for low-latency, offline, privacy-sensitive voice generation.

NewVideo

Released 1mo ago

🌍Translations 🌐Text translation 🗣️Voice cloning 👄Lip reading

Qwen3.5 LiveTranslate Flash

By Alibaba

Qwen3.5-LiveTranslate-Flash-Realtime is Alibaba’s vision-enhanced real-time audio/video translation model for live multilingual interpretation across 60 languages.

NewMultimodal

Released 1mo ago

🎙️Voiceovers 🗣️Voice cloning

Dramabox

By Resemble AI

DramaBox is Resemble AI’s expressive text-to-speech and voice-cloning model for turning screenplay-style prompts into emotional spoken performances.

NewMultimodal

Released 1mo ago

Realtime TTS 2

By Inworld AI

Realtime TTS-2 is Inworld AI’s realtime conversational text-to-speech model. It is built for live voice interaction rather than narration, with conversational awareness from prior audio turns, natural-language voice direction, crosslingual voice identity across 100+ languages, and prompt-based voice design.

NewMultimodal

Released 2mo ago

🔊Text to speech 🗣️Voice cloning 🎙️Voiceovers 🗣Dialogue generation

Sonic 3.5

By Cartesia

Sonic 3.5 is Cartesia’s fastest and most natural text-to-speech model, built for low-latency conversational voice generation across 42 languages.

NewMultimodal

Released 2mo ago

sarashina 2.2 tts

By SB Intuitions

sarashina2.2-tts is SB Intuitions’ Japanese-centric large-language-model-based text-to-speech system. It supports Japanese and English, is designed for high pronunciation accuracy, naturalness, and stability across diverse speaking styles, and includes zero-shot voice generation.

NewMultimodal

Released 2mo ago

🔊Text to speech 🗣️Voice cloning 🗣️Dialect simulation

StepAudio 2.5 TTS

By StepFun

StepAudio 2.5 TTS is StepFun’s contextual text-to-speech model with performance-oriented vocal control. It combines global and inline context guidance with zero-shot voice cloning so generated speech can follow broader style instructions as well as local delivery details, rather than just reading text flatly.

NewMultimodal

Released 2mo ago

🔊Text to speech 🎤Voice changing 🗣️Voice cloning 🎧Audiobooks 🔊Advanced audio generation

MAI Voice 1

By Microsoft

MAI-Voice-1 is Microsoft’s top-tier text-to-speech model for natural, expressive voice generation. It is built to preserve clarity, intent, speaker identity, emotional nuance, and pacing across long-form speech, and supports custom voice creation from only a few seconds of audio. Microsoft positions it for voice experiences, voice agents, and expressive spoken content at high speed and low cost.

NewAudio

Released 2mo ago

🔊Text to speech 🗣️Voice cloning 🌐Multilingual communication

MOSS TTS Nano

By OpenMOSS

MOSS-TTS-Nano is an open-source multilingual tiny speech generation model from MOSI.AI and OpenMOSS. With only 0.1B parameters, it is built for real-time TTS, can run directly on CPU without a GPU, and keeps deployment simple enough for local demos, web serving, and lightweight product integration.

NewMultimodal

Released 2mo ago

🔊Text to speech 🗣️Voice cloning 🎧Audiobooks

Pocket TTS Spokenword

By danneauxs

Pocket-TTS-Spokenword is an enhanced version of Kyutai’s Pocket TTS built for emotionally expressive audiobook generation from plain text. It adds AI emotion analysis, smart text chunking, voice adaptation, and voice cloning, while staying lightweight enough to run on CPU-only systems without requiring a GPU.

Audio

Released 3mo ago

🔊Text to speech 🎤Voice changing 🗣️Voice cloning 🔊Audio

VoxCPM2

By OpenBMB

VoxCPM2 is OpenBMB’s open-source tokenizer-free multilingual text-to-speech model for natural speech generation, voice design, and controllable voice cloning. It is a 2B-parameter model trained on over 2 million hours of speech, supports 30 languages, and produces 48 kHz studio-quality audio with real-time streaming capability.

Multimodal

Released 3mo ago

🔊Text to speech 🎤Voice changing 🗣️Voice cloning 🌐Multilingual communication

OmniVoice

By Xiaomi

OmniVoice is a multilingual zero-shot text-to-speech model built for voice cloning, voice design, and general speech synthesis at massive language scale. It supports more than 600 languages, uses a diffusion language model-style architecture, and is positioned for high-quality speech generation with fast inference.

Multimodal

Released 3mo ago

Gen 3 Wan

Wan 2.7

By Alibaba

Wan 2.7 appears to be the latest generation of the Wan AI creative model line, focused on image and video generation. The current Wan site positions the platform around text-to-image, image-to-image, text-to-video, image-to-video, and image editing workflows, suggesting Wan 2.7 is aimed at general-purpose visual content creation rather than a narrow single-task model.

🎥Videos 🎬Video editing 📽️Image to video 🗣️Voice cloning 🎤Lip sync videos

Multimodal

Released 3mo ago

🔊Text to speech 🗣️Voice cloning 🔊Voice enhancement

LongCat AudioDiT 3.5B

By Meituan

LongCat-AudioDiT-3.5B is Meituan LongCat’s diffusion-based text-to-speech model built directly in waveform latent space rather than mel-spectrogram space. It is designed for high-fidelity speech generation and zero-shot voice cloning, supports Chinese and English, and is positioned as a top-performing open model on the Seed benchmark for speaker similarity and intelligibility.

Audio

Released 3mo ago

🖼️Image generation 🗣️Voice cloning 🔍Image interpretation 🔊Audio

LongCat Next

By Meituan

LongCat Next is a multimodal LongCat model focused on compact yet capable visual and speech understanding. The official intro highlights strong performance despite a 28x compression ratio, with particular strength in text rendering, speech comprehension, low-latency voice conversation, and customizable voice cloning.

Multimodal

Released 3mo ago

🔊Text to speech 🗣️Voice cloning 🎙️Voiceovers 🎤Voice agents

Voxtral TTS

By Mistral AI

Voxtral TTS is Mistral’s new open-source text-to-speech model for building voice agents and enterprise speech applications. According to TechCrunch, it supports 9 languages, can clone a voice from under 5 seconds of audio, preserves accents and speaking style, and is optimized for real-time use on edge devices like phones, laptops, and wearables.

Audio

Released 3mo ago

🔊Text to speech 🗣️Voice cloning 🎙️Voiceovers 🎤Voice agents

Lightning v3

By Smallest AI

Lightning is Smallest.ai’s low-latency text-to-speech system for real-time voice agents, voiceovers, and voice cloning.

Audio

Released 3mo ago

🔊Text to speech 🗣️Voice cloning 🎙️Voiceovers 🎧Audiobooks

MOSS TTS Local Transformer v1.5

By OpenMOSS

MOSS-TTS-Local-Transformer-v1.5 is a 5B-parameter text-to-speech model supporting 31 languages with zero-shot voice cloning, long-form speech generation, token-level duration control, Pinyin/IPA pronunciation control, code-switching, and 48 kHz stereo audio output via MOSS-Audio-Tokenizer-v2.

Audio

Released 3mo ago

🔊Text to speech 🗣️Voice cloning 🗣️Speech to speech 🎙️Voiceovers

TADA 1B

By Hume AI

TADA-1B is a unified speech-language model checkpoint that aligns text tokens and speech representations 1-to-1 for fast, reliable text-to-speech generation.

Audio

Released 3mo ago

🔊Text to speech 🗣️Voice cloning 🗣️Speech to speech 🎙️Voiceovers 🌐Multilingual communication

TADA 3B ML

By Hume AI

TADA-3B-ml is a multilingual TADA checkpoint built for fast, reliable speech generation using the same 1-to-1 text-acoustic alignment framework.

Multimodal

Released 3mo ago

🔊Text to speech 🎤Voice changing 🗣️Voice cloning 🎙️Voiceovers

Qwen3 TTS

By Alibaba

Qwen3-TTS is a speech generation model family designed for high-quality, human-like TTS with voice cloning and natural-language control over voice style.

Audio

Released 4mo ago

🎥Video avatars 🎬Video dubbing 🗣️Voice cloning 🎭Face swap

DreamID-Omni

By Guoxu1233

DreamID-Omni is a human-centric audio-video generation framework that supports reference-conditioned generation, identity-and-voice video editing, and audio-driven identity animation with lip-sync.

Multimodal

Released 4mo ago

Zyphra

By Zyphra AI

Zonos-v0.1 is Zyphra’s open-weight text-to-speech family, two 1.6B models trained on 200k+ hours of multilingual speech, offering expressive, real-time TTS and high-quality voice cloning.

Audio

Released 4mo ago

🎤Singing 🗣️Voice cloning 🔊Voice matching 🎤Vocal isolation

SoulX Singer

By Soul AILab

SoulX-Singer is a high-fidelity, zero-shot singing voice synthesis model that generates realistic singing voices for unseen singers, with melody-conditioned (F0 contour) and score-conditioned (MIDI) control.

Multimodal

Released 5mo ago

LuxTTS

By ysharma3501

ZipVoice-based voice cloning TTS that generates 48 kHz speech at up to 150x real time, fitting in about 1 GB VRAM for local, high quality synthesis

Audio

Released 5mo ago

Minimax Speech 2.8 Turbo

By MiniMax

Latency-optimized sibling of Speech-2.8-HD, trading a bit of ultimate fidelity for faster, cheaper generation while keeping multilingual, emotional, voice-cloning strengths.

Audio

Released 5mo ago

Minimax Speech 2.8 HD

By MiniMax

High-definition MiniMax TTS model focused on studio-grade, multilingual speech, rich emotion control, interjections and voice cloning for premium voiceovers and production audio.

Audio

Released 5mo ago

Gen 4 Qwen

Qwen3 TTS 12Hz 1.7B CustomVoice

By Alibaba

Qwen’s open text-to-speech model supporting multilingual speech generation with custom voice capability.

Audio

Released 5mo ago

Gen 7

Chroma 1.0

By Flash Labs

FlashLabs Chroma 1.0 is a real-time spoken dialogue model that interleaves text and audio tokens to enable sub-second, end-to-end conversations with personalized voice cloning and high speaker similarity.

🗣️Voice cloning 🔊Text to speech

Text

Released 5mo ago

Gen 4 Qwen

Qwen3 TTS VC Flash

By Alibaba

Qwen3-TTS-VC-Flash is Qwen’s VoiceClone voice-conversion model that clones any speaker from about 3 seconds of audio, then revoices speech in that identity across 10 languages with low word-error rates.

Audio

Released 6mo ago

🔊Text to speech 📚Database Q&A 🗣️Voice cloning

VoxCPM 1.5

By OpenBMB

VoxCPM1.5 is OpenBMB’s tokenizer-free TTS model that generates expressive, context-aware speech and realistic zero-shot voice clones in Chinese and English, with real-time streaming and open-source weights that support full and LoRA fine-tuning.

Audio

Released 6mo ago

Minimax Speech 2.6 HD

By MiniMax

High-quality version of MiniMax Speech 2.6, focused on ultra-natural voice, Fluent LoRA cloning and robust handling of complex text formats across many languages.

Audio

Released 8mo ago

FireRedTTS-2

By FireRedTeam

FireRedTTS-2 is a long-form streaming TTS system for multi-speaker dialogue generation.

Audio

Released 10mo ago

🔊Text to speech 🎤Voice changing 🗣️Voice cloning

MiniMax Speech 2.5

By MiniMax

MiniMax Speech 2.5 is a multilingual voice generation model that boosts naturalness and cloning fidelity across 40 plus languages, reducing mechanical tone and preserving accent, age and emotion for high-quality TTS.

Audio

Released 11mo ago

Zonos 0.1 hybrid

By Zyphra AI

Open-weights text-to-speech model focused on expressive, high quality speech generation with voice cloning and controllable attributes like speaking rate, pitch variation, and emotions.

Multimodal

Released 1y ago

Gen 4 Eleven

Eleven v3 alpha

By Eleven Labs

Eleven v3 (alpha) is ElevenLabs’ next-gen speech model for lifelike TTS, dubbing, and speech-to-speech. It adds richer emotion control, stronger multilingual and cross-lingual voice preservation, lower latency streaming, and cleaner timing for studio and real-time uses.

Audio

Released 1y ago

🔊Text to speech 🔄Image swapping and video animation 🗣️Voice cloning

Minimax Speech 2.0 HD

By MiniMax

High-fidelity Speech-02 model using AR Transformer plus Flow-VAE, aimed at top-tier zero-shot TTS quality and benchmark-leading naturalness.

Audio

Released 1y ago

Orpheus TTS

By Canopy Labs AI

Orpheus TTS is Canopy Labs’ Llama-based 3B speech LLM for natural, emotionally controllable, multilingual text-to-speech with real-time streaming and voice cloning.

Audio

Released 1y ago

MiniMax Speech 1.0 Turbo

By MiniMax

Speed-focused Speech-01 variant delivering fast, natural TTS for everyday use while the HD version targets maximum fidelity and cloning quality.

Audio

Released 1y ago

🔊Text to speech 🗣️Voice cloning 🗒Transcription

MiniMax Speech 1.0 HD

By MiniMax

High-definition T2A-01 speech model with hundreds of preset voices, rich emotion control and rapid few-second voice cloning across many languages.

Audio

Released 1y ago

Fish Speech

By Fish Audio

Fish-Speech is an open multilingual text-to-speech system that uses large language models for linguistic understanding to generate natural, expressive speech and support voice cloning.

Audio

Released 2y ago

🎤Voice agents 🔊Text to speech 🗣️Voice cloning 🗒Transcription

Raon-Speech

By KRAFTON

Raon-Speech is KRAFTON’s open-source 9B bilingual speech language model for English and Korean. It is built as a unified speech AI system that supports speech-to-text, text-to-speech, spoken QA, speech chat, and text QA, with low-latency generation and optional speaker-conditioned TTS.

Multimodal

Released 2y ago