正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

New realtime AI voice, Sophon Realtime. Open source & Apache 2.

AI Search

28,453 subscribers

37,196 次观看 • 1 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

12 条评论

Utku Çoban 的头像

Utku Çoban1 天前

Only 40GB of weights

ashen 的头像

ashen1 天前

amazing wtf

GD 的头像

GD1 天前

Super nice. Does this support tool calling ? If yes, how accorate it is for building customer care kind of voice agents? Available anywhere as API ? If yes, cost ?

Dawid Drzewicki 的头像

Dawid Drzewicki1 天前

Nice but for such huge model I would expect better let’s be honest it’s not the smallest

ᒎᘴᓵᖶᓋ 的头像

ᒎᘴᓵᖶᓋ1 天前

Apache 2 realtime voice is a gift. Does it run decent on a Mac yet?

Sahil kashyap 的头像

Sahil kashyap1 天前

@antirez @ivanfioravanti I see you guys do awesome things with apple MLX/mps, is it possible to do your magic on this ? Thanks for your creations help me a ton.

Steve Defendre 的头像

Steve Defendre1 天前

🔥

Kent 的头像

Kent1 天前

#chefcheck

M7md 的头像

M7md1 天前

@grok check the repo ,and tell me specs it needs

Iris 的头像

Iris1 天前

rapid-fire questions are the easy part, what about interrupting it mid-word

luis 的头像

luis1 天前

@Presidentlin

Tien McCurry 的头像

Tien McCurry1 天前

40gb, no cloning? Nah

相关视频

Announcing Kontext Realtime, an open-source web app for editing images with voice commands.

Announcing Kontext Realtime, an open-source web app for editing images with voice commands.

Zeke Sikelianos

46,022 次观看 • 1 年前

Microsoft just dropped VibeVoice-Realtime-0.5B Open-source realtime TTS AI model that starts talking in ~300 ms Streaming, long-form and insanely fast.

Microsoft just dropped VibeVoice-Realtime-0.5B Open-source realtime TTS AI model that starts talking in ~300 ms Streaming, long-form and insanely fast.

Min Choi

80,970 次观看 • 11 个月前

Ok this realtime AI voice sounds pretty damn real.

Ok this realtime AI voice sounds pretty damn real.

AI Search

65,227 次观看 • 18 天前

Here’s OpenAI’s latest realtime voice model, GPT-Realtime-2, wired up to OpenClaw. It’s amazing. Realtime continuous chat and fast OpenClaw agent action on real tasks. Truly excellent.

Here’s OpenAI’s latest realtime voice model, GPT-Realtime-2, wired up to OpenClaw. It’s amazing. Realtime continuous chat and fast OpenClaw agent action on real tasks. Truly excellent.

Ben Badejo

143,437 次观看 • 6 个月前

Hands-on Hallucination session: New camera angle, magic clay, and an additional light source. #AI #StableDiffusion #Realtime

Hands-on Hallucination session: New camera angle, magic clay, and an additional light source. #AI #StableDiffusion #Realtime

Hugues Bruyère

19,749 次观看 • 1 年前

Z AI drops a realtime video generator for talking characters. Free & open source. Simply add a script, upload a voice & character, and it renders the video almost instantly. Btw, Z.ai is also behind one of the best open models, GLM 🔥🔥🔥

Z AI drops a realtime video generator for talking characters. Free & open source. Simply add a script, upload a voice & character, and it renders the video almost instantly. Btw, Z.ai is also behind one of the best open models, GLM 🔥🔥🔥

⚡AI Search⚡

41,477 次观看 • 10 个月前

the new OpenAI realtime voice model just released + gpt 5.5 fast mode brings us a new possibility - realtime speech to live presentation! i just talk, and the whiteboard would whiteboard itself prototype is open sourced. details in thread below -

the new OpenAI realtime voice model just released + gpt 5.5 fast mode brings us a new possibility - realtime speech to live presentation! i just talk, and the whiteboard would whiteboard itself prototype is open sourced. details in thread below -

Kun Chen

115,450 次观看 • 6 个月前

Oh my…FlashLabs releases Chroma 1.0, first open-source real-time speech-to-speech model with personalized voice cloning. Native speech-to-speech with <150ms latency & voice cloning from seconds of audio. Finally, an open alternative to OpenAI Realtime.

Oh my…FlashLabs releases Chroma 1.0, first open-source real-time speech-to-speech model with personalized voice cloning. Native speech-to-speech with <150ms latency & voice cloning from seconds of audio. Finally, an open alternative to OpenAI Realtime.

Alvaro Cintas

46,151 次观看 • 9 个月前

Introducing an open-source template for broadcasting realtime transcripts. • Generate live transcripts with Scribe • Broadcast to many using Supabase • Translate with Chrome’s built-in AI Demo and open source template below.

Introducing an open-source template for broadcasting realtime transcripts. • Generate live transcripts with Scribe • Broadcast to many using Supabase • Translate with Chrome’s built-in AI Demo and open source template below.

ElevenLabs Developers

28,114 次观看 • 1 年前

OpenAI just dropped GPT-Realtime-2, Realtime-Translate and Realtime-Whisper. Reason. Translate. Transcribe. In real time.

OpenAI just dropped GPT-Realtime-2, Realtime-Translate and Realtime-Whisper. Reason. Translate. Transcribe. In real time.

Min Choi

60,081 次观看 • 6 个月前

Crawling websites with the Realtime API 🗣️ Steer an AI agent with your voice as it crawls and browses websites in real time. Powered by OpenAI's new Realtime API, function calling, and . Check it out:

Crawling websites with the Realtime API 🗣️ Steer an AI agent with your voice as it crawls and browses websites in real time. Powered by OpenAI's new Realtime API, function calling, and . Check it out:

Eric Ciarla (hiring)

49,090 次观看 • 2 年前

Inworlds new Realtime TTS-2 model just dropped

Inworlds new Realtime TTS-2 model just dropped

Luis Catacora

25,148 次观看 • 6 个月前

Realtime speech-to-text for developers building conversational apps, AI agents, and voice workflows.

Realtime speech-to-text for developers building conversational apps, AI agents, and voice workflows.

ElevenLabs Developers

17,053,369 次观看 • 6 个月前

Introducing Realtime TTS-2, a new generation of voice model built for realtime conversation. It is the first voice model that hears the conversation, takes natural-language voice direction, holds one voice identity across over 100 languages, and speaks like a person who is paying attention. The result is voice AI that feels as good as it sounds. Try it out: Learn More:

Introducing Realtime TTS-2, a new generation of voice model built for realtime conversation. It is the first voice model that hears the conversation, takes natural-language voice direction, holds one voice identity across over 100 languages, and speaks like a person who is paying attention. The result is voice AI that feels as good as it sounds. Try it out: Learn More:

Inworld AI

327,778 次观看 • 6 个月前

Voice agents, now on Vercel. Realtime, speech and transcription are now live on AI Gateway. Build with 𝚞𝚜𝚎𝚁𝚎𝚊𝚕𝚝𝚒𝚖𝚎, 𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝚂𝚙𝚎𝚎𝚌𝚑 & 𝚝𝚛𝚊𝚗𝚜𝚌𝚛𝚒𝚋𝚎 on AI SDK 7.

Voice agents, now on Vercel. Realtime, speech and transcription are now live on AI Gateway. Build with 𝚞𝚜𝚎𝚁𝚎𝚊𝚕𝚝𝚒𝚖𝚎, 𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝚂𝚙𝚎𝚎𝚌𝚑 & 𝚝𝚛𝚊𝚗𝚜𝚌𝚛𝚒𝚋𝚎 on AI SDK 7.

Vercel

659,485 次观看 • 4 个月前

Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold. Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.

Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold. Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.

OpenAI

3,671,826 次观看 • 6 个月前

Mark Zuckerberg just unveiled Muse Realtime Avatar, our real-time embodiment technology that turns Muse Realtime Voice into expressive, interactive avatars. Muse Realtime Avatar enables an entirely new range of interactions in Muse, starting with real-time conversations. 🧵👇 #MetaConnect

AI at Meta

118,400 次观看 • 1 个月前

The open ai realtime api is sick! I hooked it up to control my browser so I could browse the web with my voice 🤯

The open ai realtime api is sick! I hooked it up to control my browser so I could browse the web with my voice 🤯

Sawyer Hood

322,177 次观看 • 2 年前

Restyling mickey in realtime with fal source code :

Restyling mickey in realtime with fal source code :

Lovis Odin

17,230 次观看 • 4 个月前