---
title: "AlphaSignal Audio: Voice Cloning News"
url: "https://alphasignal.ai/topic/audio/voice-cloning"
description: "Latest AI and machine learning news about Voice Cloning (Audio) on AlphaSignal."
---

# AlphaSignal Audio: Voice Cloning News

Latest AI and machine learning news about Voice Cloning (Audio) on AlphaSignal.

## Articles

- [Kokoro-82M Clones Any Voice From a 3-Second Clip for Under $20](https://alphasignal.ai/news/kokoro-82m-clones-any-voice-from-a-3-second-clip-for-under-20.md) (2026-10-07)
- [Open-Source VieNeu-TTS v3 Turbo Runs 48 kHz Vietnamese Speech on CPUs](https://alphasignal.ai/news/open-source-vieneu-tts-v3-turbo-runs-48-khz-vietnamese-speech-on-cpus.md) (2026-10-03)
- [Suno Speech Generates Narration and Music Together in One Pass](https://alphasignal.ai/news/suno-speech-generates-narration-and-music-together-in-one-pass.md) (2026-10-01)
- [Kyutai Retrains PocketTTS With Simpler Loss, Hitting 0.90% Word Error Rate](https://alphasignal.ai/news/kyutai-retrains-pockettts-with-simpler-loss-hitting-0-90-word-error-rate.md) (2026-10-01)
- [Fish Audio's Drama 3 Lets Developers Direct AI Voice Like a Human Actor](https://alphasignal.ai/news/fish-audio-s-drama-3-lets-developers-direct-ai-voice-like-a-human-actor.md) (2026-09-23)
- [Tencent's AuK Handles 16 Audio Tasks From a Single Prompt](https://alphasignal.ai/news/tencent-s-auk-handles-16-audio-tasks-from-a-single-prompt.md) (2026-09-19)
- [Alibaba's Qwen3.8 LiveTranslate Cuts Speech Translation Lag to 2.3 Seconds](https://alphasignal.ai/news/alibaba-s-qwen3-8-livetranslate-cuts-speech-translation-lag-to-2-3-seconds.md) (2026-09-19)
- [Tencent's AuK Replaces 16 Speech Tools With One Open-Source Model](https://alphasignal.ai/news/tencent-s-auk-replaces-16-speech-tools-with-one-open-source-model.md) (2026-09-10)
- [Gradium's Voice Design Beats ElevenLabs With 72.6% Win Rate for Free](https://alphasignal.ai/news/gradium-s-voice-design-beats-elevenlabs-with-72-6-win-rate-for-free.md) (2026-09-08)
- [audio.cpp Runs Speech and Music AI up to 5x Faster Without Python](https://alphasignal.ai/news/audio-cpp-runs-speech-and-music-ai-up-to-5x-faster-without-python.md) (2026-09-01)
- [Sarvam Opens Content Studio to Dub Videos Into 11 Indian Languages](https://alphasignal.ai/news/sarvam-opens-content-studio-to-dub-videos-into-11-indian-languages.md) (2026-08-28)
- [Fish Audio Squeezes 2M Voices and Voice Cloning Into an iPhone App](https://alphasignal.ai/news/fish-audio-squeezes-2m-voices-and-voice-cloning-into-an-iphone-app.md) (2026-08-26)
- [BreezeBlue's Breeze TTS 2 Tops Open Weights Voice AI With 1,215 Elo](https://alphasignal.ai/news/breezeblue-s-breeze-tts-2-tops-open-weights-voice-ai-with-1-215-elo.md) (2026-08-25)
- [BreezeBlue's Breeze TTS 2 Clones and Designs Voices in Under 40ms](https://alphasignal.ai/news/breezeblue-s-breeze-tts-2-clones-and-designs-voices-in-under-40ms.md) (2026-08-25)
- [Tencent's AuK Merges 16 Speech Tasks Into One Open-Source Model](https://alphasignal.ai/news/tencent-s-auk-merges-16-speech-tasks-into-one-open-source-model.md) (2026-08-21)
- [Sarvam's Saaras v3 Powers Equal AI's 285M Monthly Indian Calls](https://alphasignal.ai/news/sarvam-s-saaras-v3-powers-equal-ai-s-285m-monthly-indian-calls.md) (2026-08-18)
- [Suno Brings Voice Cloning to Mobile So Anyone Can Sing Their Own Songs](https://alphasignal.ai/news/suno-brings-voice-cloning-to-mobile-so-anyone-can-sing-their-own-songs.md) (2026-08-07)
- [Sarvam AI Ships Bulbul V4 to Bring Emotional Voice to 11 Indian Languages](https://alphasignal.ai/news/sarvam-ai-ships-bulbul-v4-to-bring-emotional-voice-to-11-indian-languages.md) (2026-07-30)
- [MLX-Audio Brings 646-Language Voice Cloning to Apple Silicon Without the Cloud](https://alphasignal.ai/news/mlx-audio-brings-646-language-voice-cloning-to-apple-silicon-without-the-cloud.md) (2026-07-29)
- [Fish Audio's S2.1 Pro Beats ElevenLabs at 11x Lower Cost After $52M Raise](https://alphasignal.ai/news/fish-audio-s-s2-1-pro-beats-elevenlabs-at-11x-lower-cost-after-52m-raise.md) (2026-07-28)
- [Alibaba's Qwen-Audio-3.0-TTS Tops Speech Arena With 16-Language Voice Cloning](https://alphasignal.ai/news/alibaba-s-qwen-audio-3-0-tts-tops-speech-arena-with-16-language-voice-cloning.md) (2026-07-20)
- [Artificial Analysis Fixes the Benchmark That Let Bad TTS Models Win](https://alphasignal.ai/news/artificial-analysis-fixes-the-benchmark-that-let-bad-tts-models-win.md) (2026-07-08)
- [Zyphra's Zonos-v0.1 Challenges ElevenLabs With a Free Open-Weight Voice Model](https://alphasignal.ai/news/zyphra-s-zonos-v0-1-challenges-elevenlabs-with-a-free-open-weight-voice-model.md) (2026-07-07)
- [ebook2audiobook Turns Any Book Into a Free Voiced Audiobook Across 1158 Languages](https://alphasignal.ai/news/ebook2audiobook-turns-any-book-into-a-free-voiced-audiobook-across-1158.md) (2026-07-01)
- [Higgsfield's Seed Audio 1.0 Brings Voice Cloning and Dubbing Into Claude](https://alphasignal.ai/news/higgsfield-s-seed-audio-1-0-brings-voice-cloning-and-dubbing-into-claude.md) (2026-06-30)
- [IISc's Vāgdhenu Opens Sanskrit Chant TTS With 4.6 Expert Score](https://alphasignal.ai/news/iisc-s-vagdhenu-opens-sanskrit-chant-tts-with-4-6-expert-score.md) (2026-06-28)
- [Microsoft's MAI-Voice-2 Fools 45% of Listeners Into Thinking It's Human](https://alphasignal.ai/news/microsoft-s-mai-voice-2-fools-45-of-listeners-into-thinking-it-s-human.md) (2026-06-23)
- [Kyutai's Pocket TTS Now Speaks 6 Languages Faster Than Real-Time on CPU](https://alphasignal.ai/news/kyutai-s-pocket-tts-now-speaks-6-languages-faster-than-real-time-on-cpu.md) (2026-06-23)
- [Fish Audio Retires Bert-VITS2 and Points 8,800 Stars to Fish-Speech](https://alphasignal.ai/news/fish-audio-retires-bert-vits2-and-points-8-800-stars-to-fish-speech.md) (2026-06-15)
- [ByteDance's MegaTTS3 Clones Voices in 3 Seconds With 0.45B Parameters](https://alphasignal.ai/news/bytedance-s-megatts3-clones-voices-in-3-seconds-with-0-45b-parameters.md) (2026-06-15)
- [OmniVoice Studio Beats ElevenLabs on Accuracy Running Fully Offline for Free](https://alphasignal.ai/news/omnivoice-studio-beats-elevenlabs-on-accuracy-running-fully-offline-for-free.md) (2026-06-13)
- [Baidu's PaddleSpeech Adds Whisper large-v3-turbo and Real-Time Multilingual Streaming ASR](https://alphasignal.ai/news/baidu-s-paddlespeech-adds-whisper-large-v3-turbo-and-real-time-multilingual.md) (2026-06-12)
- [k2-fsa's OmniVoice Clones Any Voice Across 600 Languages at 40x Real-Time Speed](https://alphasignal.ai/news/k2-fsa-s-omnivoice-clones-any-voice-across-600-languages-at-40x-real-time-speed.md) (2026-06-11)
- [Fish Audio's S2 Pro Beats Closed-Source TTS Giants With 4B Open Model](https://alphasignal.ai/news/fish-audio-s-s2-pro-beats-closed-source-tts-giants-with-4b-open-model.md) (2026-06-09)
- [Boson AI's Higgs Audio v3 Speaks 15x Better Across 100 Languages](https://alphasignal.ai/news/boson-ai-s-higgs-audio-v3-speaks-15x-better-across-100-languages.md) (2026-06-08)
- [Open-Source LuxTTS Clones Voices 150x Faster Than Realtime on One GPU](https://alphasignal.ai/news/open-source-luxtts-clones-voices-150x-faster-than-realtime-on-one-gpu.md) (2026-06-05)
- [OpenBMB's VoxCPM2 Clones Voices Across 30 Languages Without Speech Tokenizers](https://alphasignal.ai/news/openbmb-s-voxcpm2-clones-voices-across-30-languages-without-speech-tokenizers.md) (2026-06-05)
- [Microsoft's MAI-Voice-2 Fools Listeners Into Preferring It Over Real Humans](https://alphasignal.ai/news/microsoft-s-mai-voice-2-fools-listeners-into-preferring-it-over-real-humans.md) (2026-06-04)
- [Boson AI's Higgs TTS 3 Brings Human Emotion to Open Voice Agents](https://alphasignal.ai/news/boson-ai-s-higgs-tts-3-brings-human-emotion-to-open-voice-agents.md) (2026-06-04)
- [Alibaba's Fun-Realtime-TTS Beats Google to Claim the #1 Speech Throne](https://alphasignal.ai/news/alibaba-s-fun-realtime-tts-beats-google-to-claim-the-1-speech-throne.md) (2026-06-03)
- [Alibaba's Qwen3-TTS Runs on Any Hardware With This Community GGUF Port](https://alphasignal.ai/news/alibaba-s-qwen3-tts-runs-on-any-hardware-with-this-community-gguf-port.md) (2026-05-11)
- [Supertone's Supertonic 3 Beats A100 GPU Models Running on a Laptop CPU](https://alphasignal.ai/news/supertone-s-supertonic-3-beats-a100-gpu-models-running-on-a-laptop-cpu.md) (2026-05-06)
- [Neuphonic's NeuTTS Clones Voices On-Device in 3 Seconds Without Cloud GPUs](https://alphasignal.ai/news/neuphonic-s-neutts-clones-voices-on-device-in-3-seconds-without-cloud-gpus.md) (2026-04-24)
- [OpenMOSS's MOSS-TTS-Nano Clones Voices in 20 Languages on a Laptop CPU](https://alphasignal.ai/news/openmoss-s-moss-tts-nano-clones-voices-in-20-languages-on-a-laptop-cpu.md) (2026-04-15)
- [Tsinghua's MimicLM Beats Top Voice Cloning Systems by Flipping Synthetic Training Data](https://alphasignal.ai/news/tsinghua-s-mimiclm-beats-top-voice-cloning-systems-by-flipping-synthetic.md) (2026-04-13)
- [OpenBMB's VoxCPM2 Drops Audio Tokenizers to Clone Any Voice in 30 Languages](https://alphasignal.ai/news/openbmb-s-voxcpm2-drops-audio-tokenizers-to-clone-any-voice-in-30-languages.md) (2026-04-07)
- [k2-fsa's OmniVoice Clones Any Voice Across 646 Languages at 40x Real Time](https://alphasignal.ai/news/k2-fsa-s-omnivoice-clones-any-voice-across-646-languages-at-40x-real-time.md) (2026-04-03)
- [Japan's NII Shows Self Voice Conversion Breaks Every Audio Watermark to Random Guessing](https://alphasignal.ai/news/japan-s-nii-shows-self-voice-conversion-breaks-every-audio-watermark-to-random.md) (2026-03-16)
- [Hitachi Teaches Whisper Jargon by Faking Mispronounced Audio, Cutting Errors 57%](https://alphasignal.ai/news/hitachi-teaches-whisper-jargon-by-faking-mispronounced-audio-cutting-errors-57.md) (2026-03-11)
- [Real-Time-Voice-Cloning Hits 60K Stars and Gets a Fresh Overhaul](https://alphasignal.ai/news/real-time-voice-cloning-hits-60k-stars-and-gets-a-fresh-overhaul.md) (2026-03-09)