开场与背景介绍
好。AI 音频方面有什么新动态？抱歉，这个标题有点误导人，因为它漏掉了“问问 Google DeepMind”。所以，我们只是大致看一下 DeepMind 一直在做些什么。如果要看 AI 音频领域的全部内容，那我们得在这儿花上大量时间，不过我很乐意带大家看看我们在 DeepMind 正在做些什么。
英文原文
All right. What's new in AI audio? I'm sorry. It's a little bit misleading because the title leaves out the Ask Google DeepMind. So, we're just kind of looking at, you know, what we've been working on at DeepMind. If we were to look at everything in AI audio, we'd be spending a lot of time here, but you know, I'd love to show you kind of what we're what we're working on at DeepMind.是的，这就是我。大家好，我是 Thor。我在 Google DeepMind 负责开发者体验，主要从事 Gemini API 和 Google AI Studio 的相关工作。
英文原文
Yeah, this is me. Hi, everyone. I'm Thor. I work on the developer experience at Google DeepMind working on the Gemini API and Google AI Studio.向大家问好。欢迎各位。我的名字是 Torsten。你好，我叫 Thor。我非常抱歉，我的法语很差。还有日语，或者写成那样。
英文原文
Uh Hello to them. As you welcome. My name is Torsten. Uh bonjour. Je m'appelle Thor. Je suis très désolé, mon français c'est très mauvais. Uh konnichiwa or writing that.你选的那些内容，我在做演讲时讲的，或者我回家时说的。
英文原文
Um That you have what you choose I make what the talk or in what I say what I talk when I go home.好了，那是为了做演示。现在我只需要确认一下，上次我做这个演示的时候，我不小心录音覆盖掉了，然后全没了。那真的很让人难过，但我们稍后会回过头来看这个。
英文原文
Okay. That was for the demo and now I just need to make sure last time I did this demo, I recorded over it and then it was all gone. That was very sad, but we'll we'll come back to that in a bit.最新模型与发布动态
是的，我们在 DeepMind 一直在忙些什么？
英文原文
Yeah, what have we been up to at DeepMind?这里有几次发布。我实际上是在 11 月加入团队的，恰好是在 Gemini 3 发布的前一天。所以我刚加入，他们就告诉我：“明天我们要发布 Gemini 3。”我当时心想：“太棒了！”虽然我什么都没做，但这感觉很棒，那是段美好的时光。
英文原文
Um There's been a couple releases. I I actually joined the team in November, literally the day before Gemini 3 was released. So, I joined and they told me, "Tomorrow we're releasing Gemini 3." And I was like, "Yay!" Didn't do anything, but it was great. It was it was a great time.最近在开源模型方面，我们发布了 Gemma 4，我想大概就是上周。是的，非常不可思议。你在那里可以做一些很酷的事情，多模态能力也内置在 Gemma 4 中。因此，Gemma 4 模型中具备音频理解能力，而且你也可以在边缘设备等端侧设备上运行它。所以那是相当令人兴奋的技术。
英文原文
Uh most recently on the open model side, we released Gemma 4, uh I think literally last week. And yeah, pretty incredible. Some cool stuff you can do there multi modality as well baked into Gemma 4. So there's audio understanding in the the Gemma 4 models and you can do that on device on kind of edge devices as well. So that is some some very exciting stuff.在生成式媒体和音频方面，大家可能对我们的图像生成模型、视频生成模型非常熟悉。显而易见，视频中也包含了音频生成。所以这大概就是目前的进展，最近在生成式媒体模型规模上有 video 3.1 light。然后对于音频模型，我们最近推出了 Gemini 3.1 flash life，这是我们的全双工、声音到声音的实时对话模型。它同样也是多模态的，所以你可以输入实时的文本、语音和视觉内容。我们稍后会来看一下这个。
英文原文
In terms of gen media and audio, you're probably very familiar with our you know, image generation models, video generation models. Obviously video has audio generation in there as well. So this is kind of where the progression is there most recently with video 3.1 light on the gen media model size and then on the audio models, we recently launched Gemini 3.1 flash life, which is our kind of full duplex, you know, sound to sound real-time conversational model. Also multimodal so you can ingest real-time text, voice, vision. Which we'll we'll look at in a in a bit.音频理解能力与 Echo Script 演示
在音频这个非常宽泛的话题上，我们所做一切的基础可以说就是前沿的 Gemini 系列模型。Gemini 3 在音频理解方面极其出色。而且这不仅仅是进行转录，而是真正理解其中所有的细微差别。那可能不仅包含言语本身，还包含言语的语境、情绪、语速，某种程度上，以及音频中波动传递的任何非纯文本的内容。
英文原文
So you know, on kind of audio very very broad topic but sort of the the baseline of everything we do are kind of the you know, frontier Gemini models. And so Gemini 3 is incredibly good at understanding audio. And you know, that's not just transcribing it but really you know, understanding kind of all the nuances that are in there. So that might be you know, obviously speech but also the context of the speech, the the emotion, you know, your pacing, your sort of yeah, anything that sort of swings within the audio that's you know, not just text.因此在音频理解方面，我们的目标是构建能够深度领会、丰富转录并通过音频进行稳健推理的模型。无缝处理各种不同语言、方言、口音和模态的大融合。无论何时何地，Gemini 在转录甚至相互交谈、重叠插话的人声时都非常出色。这是非常不可思议的，还能在不同语言之间无缝切换。
英文原文
So on the audio understanding kind of our goal is to build models that deeply comprehend, richly transcribe and robustly reason through audio. Seamlessly handling you know, a large mix of different languages, dialects, accents, and modalities. And sort of anywhere and always, you know, Gemini is really good at on you know, transcribing even people that are talking over each other. Um which is which is pretty pretty incredible, you know, seamlessly switching between different languages.这大概就是我们现在正在看的演示。Echo Script 使用了 Gemini 3 flash preview 来分析音频录音并从中提取信息。它是基于 Google AI Studio 构建的，所以你可以在 AI Studio 的展示区（gallery）找到它并亲自体验。稍后我也能把幻灯片发给你们。
英文原文
That was sort of the demo we're looking at um now. So, um Echo Script is kind of Gemini uh 3 flash preview to sort of analyze, you know, audio recordings and extract sort of information out of it. Uh it is built with Google AI Studio, so you can you can find it in the gallery in AI Studio. You can try it out. Uh I can give you the slides later as well.这就是我之前尝试演示的内容。不同于单纯的转录模型，我们向模型发送一次请求，或者在使用 API 时调用一次 API，就能从音频中提取出大量信息。大家在这里可以看到，包括摘要，还有我用名字做的自我介绍。所以我们实际上能够按名字来标记说话人的片段。我忘了现场没有爱起哄抬杠的人，否则我们也能把那种声音捕捉到。也许我们稍后看时间是否充裕再试一下。不过大家在这里可以看到，我们在提取时间戳，标注说话人、识别人是谁，我们也在识别语言以及其中的情绪，对吧？
英文原文
Um and so, that was sort of, you know, what I was trying to demo earlier. Um so, you know, different from just kind of a pure transcription uh model, we can extract a lot of information out of the audio within one single, you know, request to the model or one single API request if we're using the API. So, you can see here, you know, summary, I introduced myself by name. Um so, we're actually able to label um you know, the section with speaker by name. Uh I forgot there was no hecklers in the room, otherwise we would have picked that up as well. Uh maybe we can see if we have more time later and we can do that. But, so we can see here, you know, we're extracting timestamps, uh we're labeling the speaker, kind of identifying the speaker, we're we're identifying the language, and sort of the emotion of it, right?很高兴以 Grace 的身份介绍自己。大家可以看到这句是用德语说的。通常它会把我的德语归类为愤怒，但在这里，我想我是因为很高兴能和大家在一起。所以我只是告诉它，标出情绪，如果不是英语就标出语言种类，同时也提供一份英文翻译，对吧？法语部分归为了中性，通常人们会觉得听起来很悲伤。法语只是稍微带一点……不，我说的是“很抱歉，我的法语很烂”。听起来没有足够悲伤，所以在这里被判定为中性。
英文原文
Uh happy, you know, to introduce myself as Grace. Um now you can see this was in German. Um normally it would classify my German as angry. Uh but, uh here, you know, I I guess I'm very happy to be with you all. So, uh I just told it, you know, uh label sort of the emotion, uh label the language if it's a language that is not English, um give me an English translation as well, right? Um in French, uh neutral, normally you would say sad. Uh you know, French is just a bit more of a uh no, I said, you know, I'm sorry, my French is very bad. Uh didn't didn't sound sad enough, so neutral in this case.好吧，这个日语没有成功。要是有人懂日语的话，我得好好练习一下了；它其实应该写的是“你好，我的名字是 Thor”。可惜的是，这里识别得有点偏。看看我的中文普通话有没有好一点。“大家好，我是生活在美国的德国人。抱歉，我的中文。”是的，那是对的。在座有人能看懂中文吗？没有，好的。那我们就姑且相信这是对的。
英文原文
Um Okay, this uh this didn't work so much Japanese. I got to got to practice that if anyone reads Japanese, so it should actually say hello, my name is Thor. Unfortunately, bit of a miss there. Uh let's see if my Mandarin was any better. Hello everyone, I'm a German living in the United States. Sorry, my Chinese. Yeah, that is uh correct. Does anyone read Chinese in the room? No, okay. Well, uh we'll just trust that that is um that is correct.单次 API 调用与结构化输出
所以大家可以看到，这是向模型发起的一次请求。我基本上只是告诉它：区分出不同的说话人；如果有上下文，就用名字来标记说话人；给出准确的时间戳；给出语言；如果语言不是英语，就给出翻译；在开心、悲伤、愤怒、中性之中识别出情绪；并在开头提供对整段音频的简短摘要。
英文原文
Uh and so, we can see here that um this was, you know, one uh kind of request to the model um where, you know, I basically just told it identify the distinct speakers. If you have contacts, you know, label it by name label the speakers by name. Give me the accurate timestamps. Give me the language. If the language is not English, give me the translation. Uh identify the emotion out of, you know, happy, sad, angry, neutral. And then also provide a brief summary of the entire audio at the beginning.这只是对 Gemini 3 Flash preview 进行的一次 API 调用，我们就提取出了所有这些信息。我直接给它指定了一个响应模式（response schema），也就是结构化输出，然后我就能直接把这些数据填充到我的 API 和 UI 中，形成这样的结构。
英文原文
So, this was one API call uh to Gemini 3 Flash preview. And, you know, we got all this information out. We could, you know, I just gave it a response schema so kind of structured outputs, uh and I was able to just populate that into my into my API into my UI to have sort of the structure.语音生成与声音库机制
因此，这种音频理解能力以及 Gemini 3 模型的基础研究，正是驱动语音生成以及实时对话生成的基础。具备这种音频理解能力对于知晓特定声音的听觉特征非常有帮助，包括不同的语速、不同的口音以及类似的各种场景。
英文原文
So, you know, this kind of audio understanding and sort of the the, you know, base research in the Gemini 3 models, that is sort of what powers um the speech generation as well as well as the you know, real-time conversational um generation. So, having that audio understanding um is is really really great in terms of, you know, knowing what certain things sound like including, you know, different pacing, different accents and and and scenarios like that.我们所有模型的基础目前正是 Gemini 3 的基础研究成果，随后我们在其之上构建专门的音频模型。
英文原文
So, you know, the foundation of kind of all our models is now sort of the the Gemini 3 foundational research and then we're building kind of the dedicated audio models on on top of that.语音生成在这方面就稍有不同。如果大家以前用过其他 TTS（文本转语音）提供商的服务，你可能会有一个庞大的音色库，包含很多不同的声音，然后按性别、按口音、按语言等各种条件来进行筛选。但在 Gemini 中，大概只有 30 来种基础声音。接下来你要做的是引导该声音以特定方式去表现。由于我们具备这种音频理解能力，我们基本上可以调整声音，让它以某种方式说话，或者带上特定的口音。这样我们就能从一组数量较少的基础声音出发，演变为我们在语音生成中想要的非常具体的声音。
英文原文
And so, with speech generation it's a bit different. You know, if you've used kind of other TTS providers before, you probably have a huge library of, you know, different voices that you sort of, you know, you filter by gender, by by, you know, accent, by languages, what have you. But so, in in in Gemini, you have, you know, just I think it's like 30-ish sort of base voices. And then what you do is you you kind of direct that voice to act in a certain way. And again, because we have that audio understanding, we can we can basically modify the voice to, you know, act in a certain way, to, you know, use a certain accent. And so, we can go from kind of a small set of of base voices to a very specific, you know, kind of voice that we're looking for for our speech generation.这里同样有一个可以试用的小应用程序。它也收录在 Google AI Studio Gallery 中，被称为“voice library（声音库）”。我们能做的是，结合刚才看到的提示词结构，构建出音频档案、场景，设定好情境，给出导演指导般的说明。因此，我们为接下来的……提供指导。
英文原文
Again, there's a a little application that you can try out. It's in the Google AI Studio Gallery as well. It's called the voice library. And so, what we can do is, you know, kind of giving the the the prompt structure that we just saw, you know, we're building sort of the the audio profile, the scene, we're setting the scene, we're instructing sort of this director's note. So, we're giving guidance for the语音风格定制与导演提示
表演，你知道，就像你指导真人以某种方式表演一样。还有一些样本上下文以及我们想要的类似转录文本。所以现在我们可以做的就是，我们刚才说想要一个偏高音调的爱尔兰男性声音。基本上我在这里再次使用了 Gemini 3 Flash 来构建我们用于语音生成的系统提示词。所以我们在这里说，我们正在设定我们的音频配置文件，比如这里的 Finian 处在克莱尔郡沿海一家舒适而拥挤的酒吧场景中。用浓重纯正的爱尔兰口音来念台词。
英文原文
performance,you
know,
just
like
how
you
would
direct
a
human,
you
know,
to
to
act
out
a
certain
way.
And
and
some
sample
context
and
kind
of
the
transcript
um,
that
we
want.
So,
now
what
we
can
do
is,
you
know,
we
we
just
said
sort
of
uh,
we
want,
you
know,
high
pitch
Irish
male.
Uh,
and
so
basically,
I
just
used
Gemini
um,
3
flash
here
again
to
then
construct
our
um,
system
prompt
for
the
speech
generation.
So,
we're
saying
here,
you
know,
um,
we're
we're
setting
sort
of
our
audio
profile,
you
know,
Finian
here
in
the
scene
sort
of
cozy
crowded
pub
uh,
in
the
coast
of
County
Clare.
Um,
you
know,
deliver
the
lines
with
a
strong
authentic
uh,
Irish
accent.
现在我们希望 TPU 不要让我失望。开始吧。它失败了。不过我有所准备，所以我们可以在这里听一下。
英文原文
Andso
now
we
hope
the
the
TPUs
don't
uh,
disappoint
me.
There
we
go.
It
failed.
But
um,
I
didn't,
you
know,
I
prepared
it
so
we
can
we
can
listen
to
it
here.
“啊，除非亲眼所见，否则你绝不会相信那东西有多大，我跟你讲。那真是一团糟，确实是，等到夜幕降临时我们都快笑破肚皮了。”
英文原文
Ah,you
wouldn't
believe
the
size
of
the
thing
until
you
saw
it
with
your
own
two
eyes,
I'm
telling
you.
It
was
a
grand
old
mess,
so
it
was,
and
we
were
all
laughing
fit
to
burst
by
the
end
of
the
night.
如大家所见，这里的基础声音是这个：“我们可以解决什么样的问题？”那是相当标准的美式口音。但现在通过给它那个导演指示，我们就可以呈现出：
英文原文
So,as
it
as
you
can
see,
you
know,
this
was
uh,
the
the
base
voice
here
is
uh,
this
one.
What
kind
of
problem
could
we
solve?
So,
you
know,
that
is
a
fairly
sort
of
stan-
standard,
you
know,
American
accent.
But
so
now
by,
you
know,
giving
it
that
director's
node,
we
can
then
sort
of
give
“啊，除非亲眼所见，否则你绝不会相信那东西有多大，我跟你讲。那真是一团糟，确实是，我们都快笑破……”
英文原文
>> Ah,you
wouldn't
believe
the
size
of
the
thing
until
you
saw
it
with
your
own
two
eyes,
I'm
telling
you.
It
was
a
grand
old
mess,
so
it
was,
and
we
were
all
laughing
fit
或者类似地，我们这里有 Zephyr。这个声音在这里：“今天准备好构建一些厉害的东西了吗？”同样，这是一种相当标准的美式英语口音。现在我们可以说，给它一种新加坡式的特点。
英文原文
Or,you
know,
similarly
here
we
have
um,
Zephyr.
So,
this
voice
uh,
is
here.
Ready
to
build
something
awesome
today?
Again,
you
know,
kind
of
fairly
standard
sort
of
American
um,
English
accent
here.
And
now
we
could
say,
you
know,
give
it
kind
of
a
Singaporean
sort
of
C.
“哇，你一定要试试这个海南鸡饭啦。辣椒绝对保准 confirm plus chop 你会喜欢的。趁安哥关店前赶紧排队，知道吗？”
英文原文
Wah,you
must
try
this
chicken
rice
lah.
The
chili
is
damn
sure
confirm
plus
chop
you
will
love
it.
Faster
queue
before
the
uncle
close
shop,
okay?
有人在新加坡呆过吗？是的，这就是你在小贩中心会听到的声音。同样，这背后是以音频理解为支撑的。模型真正理解这些不同场景听起来是什么样子的，然后可以修改语音生成以达到那种效果。
英文原文
Anyonespend
time
in
Singapore?
You
know,
yeah.
That's
you
know,
that's
something
you
would
hear
in
the
Hawker
Center.
So,
again,
you
know,
that
is
kind
of
underpinned
by
the
audio
understanding.
So,
the
model
really
understands
what,
you
know,
these
these
different
scenarios
sound
like
and
then
can
modify
the
speech
generation
to
to
be
like
that.
Um
原生实时多模态与 Gemini Live
是的，最后是原生音频声到声的多模态实时功能。我们在几周前刚刚推出了 Gemini 3.1 Flashlight。它是一个语音到语音的实时多模态模型。你可以通过 WebSocket 连接实时输入文本、音频和视频，然后获得实时的音频响应以及文本转录。
英文原文
Yes,and
then,
you
know,
finally
sort
of
the
the
native
audio
sound
to
sound
multimodal
real
time.
So,
we
just
launched
a
couple
weeks
ago
Gemini
3.1
Flashlight.
So,
it
is
a
speech
to
speech
is
kind
of
real-time
multimodal
model.
You
can
ingest
text,
audio,
video
in
real
time
through
a
web
socket
connection
and
then
you
get
real-time
audio
response
back
as
well
as
kind
of
text
transcript
of
that.
Um
显然，基准测试，尤其是在音频领域，其实是不可全信的。可以看到它的推理和思考过程，这非常棒。在这里，思考、推理和智能是直接嵌入在模型中的。这不同于级联流水线，后者实际上需要先经过文本，再经过 LLM 来获取智能。而在这里，智能直接内置于音频模型中，这就是不同之处。
英文原文
Youknow,
obviously
benchmarks
are,
you
know,
especially
in
the
audio
space,
benchmarks,
you
know,
can't
really
trust
them.
You
know,
it's
great
you
can
see
sort
of
the
reasoning,
the
thinking.
So,
so
here
the
the
thinking
and
the
reasoning
and
the
intelligence
is
baked
directly
into
the
model.
So,
that's,
you
know,
different
from
a
cascading
pipeline
where
you
would
actually
go
through
text
to
then
go
through
an
LLM
to
get
the
intelligence.
Here,
you
know,
the
intelligence
is
baked
into
the
audio
model.
So,
that's
kind
of
the
difference
there.
不过显然在实际场景中，大家可以在 ai.studio/live 进行体验。AI Studio 的一大优势在于你可以免费试用。这让你可以试用这些模型，而无需绑定信用卡。所以 AI Studio 是一个非常好的尝试途径。
英文原文
Umbut
obviously
in
in
real
scenarios,
you
know,
you
can
try
this
out
in
ai.studio/life.
So,
the
great
thing
with
AI
Studio
is
you
can
try
it
out,
you
know,
without
paying
anything.
So,
this
is
allows
you
to,
you
know,
try
kind
of
the
models
without
actually
needing
to
put
down
the
credit
card.
So,
AI
Studio
is
a
is
a
really
great
way
to
do
that.
同样，这里的模型也内置了音频理解能力。所以我们可以做的就是给它一些系统指令，比如“用友好的爱尔兰口音说话”。同时，我们也可以在这里接入摄像头画面。然后我们可以问：“嘿，你能看到我吗？”
英文原文
Andagain,
you
know,
we
have
the
audio
understanding
kind
of
baked
into
the
model
here.
So,
what
we
can
do
is
we
can
give
it
some
system
instructions,
you
know,
for
example,
speak
in
a
friendly
Irish
accent.
And
then
also
we
can
ingest
kind
of
our,
you
know,
camera
here
for
example.
And
then
we
can
say,
"Hey,
can
you
see
me?"
“哎呀，你好啊。我能清清楚楚地看到你，确实可以。你今天有什么想法？”
英文原文
Well,hello
there.
I
can
see
you
loud
and
clear,
so
I
can.
What's
on
your
mind
today?
“你觉得我的穿着怎么样？”
英文原文
Whatdo
you
think
of
my
outfit?
“啊，看看穿着 Gemini 衬衫的你。看起来真是棒极了。反戴的帽子给你增添了一种十足的随性范儿，确实如此。看起来很精神帅气。”
英文原文
Ah,look
at
you
with
your
Gemini
shirt.
It
looks
grand
altogether.
And
the
backwards
hat
gives
you
a
fierce
laid-back
vibe,
so
it
does.
You're
looking
sharp.
“啊，太棒了。你能给我念一首德语诗吗，拜托？”
英文原文
Ah,wunderbar.
Kannst
du
mir
ein
Gedicht
auf
Deutsch
erzählen,
bitte?
“啊，德语诗是吧？当然，我可以为你试试。这里有一首小诗。”
英文原文
Ah,poem
in
German,
is
it?
Sure,
I
can
give
that
a
go
for
you.
Here's
a
little
one.
“从前有一束微光，照耀得如此明亮温柔。它把喜悦带进每颗心灵，驱散了忧伤与痛苦。”
英文原文
Eswar
einmal
ein
kleines
Licht,
das
strahlte
so
hell
und
mit.
Es
brachte
Freude
in
jedes
Herz,
vertrieb
den
Kummer
und
den
Schmerz.
现在有趣的是，它实际上把爱尔兰口音也应用到了德语上。所以显然你需要调整一下系统指令，让它不要在每种语言里都带有爱尔兰口音。不过这很有趣，你可以在不同的语言之间来回切换。
英文原文
So,what
was
the
What's
funny
here
now
is
it
actually
applies
the
Irish
accent
to
the
German
as
well.
So,
obviously
you
need
to
kind
of
adjust
your
system
instructions
to
you
know,
not
speak
in
an
Irish
accent
in
any
every
language.
But
so
it
it's
pretty
funny
you
can
kind
of
switch
between
the
different
languages
there.
同样，在 ai.studio/live 上大家可以试用它。你也可以接入屏幕画面，所以基本上就是在音频之外输入视频帧，目前最大的帧率为每秒一帧，这是当前可以输入的最大限制。
英文原文
Again,so
ai.studio/live,
you
can
try
it
out.
You
could
also
ingest
your
screen,
so
you're
basically
just
ingesting
video
frames
in
addition
to
the
audio
at
a
maximum
frame
rate
of
one
frame
per
second
at
the
moment.
That's
that's
kind
of
the
maximum
you
can
ingest.
这里有几个示例，如果你自己是开发者，欢迎试用。它们在文档中也有链接。这些示例展示了如何上手，比如用 Python 建立服务器到服务器的连接，或者用 JavaScript 建立客户端到服务器的连接。大家可以在这里找到它们。
英文原文
Umthere
is
a
couple
examples,
you
know,
if
you're
developer
yourself,
feel
free
to
try
these
out.
They
are
linked
from
the
docs
as
well.
These
are,
you
know,
just
some
examples
of
how
you
would
get
started
say
in
Python
for
like
a
server
to
server
connection
or
in
JavaScript
with
kind
of
a
client
to
server
connection.
So,
you
can
find
those
here.
另外也推荐 Gemini skills。我们为各类 Gemini API（包括 Live API）都发布了编程智能体技能。与实时音频打交道可能会更具挑战性一些。因此，使用这些智能体技能并将它们安装到你的编程智能体中，能切实帮助引导它们走在正确的方向上，并带来你所期望的结果。
英文原文
Uhalso
recommend
the
Gemini
skills.
So,
we
have
published
coding
agent
skills
for
kind
of
all
of
the
Gemini
APIs
including
the
life
API.
So,
you
know,
real-time
audio
working
with
real-time
audio
can
just
be
a
bit
more
challenging.
So,
uh
using
these
agent
skills
and
kind
of
installing
them
in
your
uh
you
know,
coding
agents
can
really
help
steer
them
sort
of
in
the
right
way
and
give
you
sort
of
that
result
that
you're
looking
for.
音乐生成模型 Lyra 3 与 Live Jukebox
最后，我们还有——好的，我们还有一点时间。音乐，同样也是音频，所以我把它放到了这里。我们最近发布了 Lyra 3。是的，它是一个音乐生成模型。不过现在它实际上可以生成带有歌词的音乐。有两个独立的模型：一个是 Lyra 3 Clip，它是一个 30 秒短旋律生成模型；另一个是 Lyra 3 Pro，是完整长度的歌曲生成模型。
英文原文
Umlastly,
we
have
Okay,
we
have
a
bit
of
time.
So,
music.
Uh
you
know,
also
audio.
So,
I
put
that
in
here.
Uh
we
recently
released
Lyra
So,
yeah,
it's
it's
a
music
generation
model.
Um
but
so,
it
it
now
actually
can
generate
music
with
lyrics.
There's
two
separate
models.
There's
a
Lyra
3
clip
which
is
a
30-second
kind
of
jingle
genera-
generation
model
and
then
a
Lyra
3
Pro
is
the
full-length
uh
song
generation
model.
把所有这些整合在一起，不知道大家是否还记得过去给广播电台打电话点歌的美好旧时光。所以我构建了这样一个名为 Live Jukebox 的应用程序。现在我们可以试用一下，我们实际上给实时 Gemini Live 模型提供了一个工具，用于调用 Lyra 来生成歌曲。让我们看看能否在这里实现。
英文原文
Umand
so,
I
you
know,
kind
of
bringing
everything
together.
I
don't
know
if
you
remember
the
good
old
days
when
you
would
actually
call
the
radio
station
and
wish
for
a
song.
Um
and
so,
I've
I've
kind
of
built
this
application
um
called
Life
Jukebox.
And
so,
we
can
now
try
it
out
where
um
we
actually
give
the
the
real-time
Gemini
Life
model
uh
a
tool
to
then
generate
a
song
using
Lyra.
And
so,
let's
see
if
we
can
if
we
can
do
that
here.
“好了，您正在与点唱机 DJ 进行实时连线。太棒了。请问我是和哪位在通话，我们今天打算整出什么样的氛围？是地道的锐舞风格，还是来点别的……”
英文原文
Rightthen,
you're
live
on
air
with
the
jukebox
DJ.
What
an
absolute
legend.
Who
am
I
speaking
to
and
what
kind
of
vibe
are
we
going
to
cook
up
today?
Is
it
a
proper
rave
style
or
something
a
bit
more
“我们能来一首关于英国初创圈的德式 Techno 流行歌吗？”
英文原文
>> weget
maybe
a
German
techno
Schlager
about
the
UK
startup
scene?
“关于英国初创圈的德式 Techno 流行歌？朋友，这太有颠覆性了。我太喜欢了。好的，想象一下这个画面：强劲的 Techno 节拍，地道的汉斯·季默风格。”
英文原文
Germantechno
Schlager
about
the
UK
startup
scene?
Mate,
that
is
revolutionary.
I
love
it.
Right,
picture
this.
Pounding
techno
beat,
a
proper
Hans
Zimmer
style.
“太棒了。开始吧，就这么整。”
英文原文
>> great.Let's
go.
Let's
do
that.
“坐稳了，我们马上就好。只是为了确保它绝对是一首爆款神曲：歌词里有没有什么你特别想加入的英国初创圈流行热词或故事？而且你倾向于狂躁有力的能量，还是那种在 Techno 狂热中带点旋律感的东西？”
英文原文
Holdon
tight,
we're
almost
there.
Just
to
make
sure
it's
a
certified
banger.
Any
specific
buzzwords
or
stories
from
the
UK
startup
world
you
want
in
the
lyrics?
And
I'll
be
thinking
manic
energy
or
something
a
bit
more
melodic
within
that
techno
madness.
“狂躁的能量，歌词就给我个惊喜吧。”
英文原文
>> manicenergy
and
surprise
me
on
the
lyrics.
“没问题，收到。准备好轰炸你的耳膜吧。狂躁的德式 Techno 流行歌，融入英国初创公司特色。正在为你打造一首地道的爆款曲目。来听听看。”
英文原文
Allright,
you're
on.
Get
ready
to
have
your
eardrums
blasted.
Manic
German
techno
Schlager
with
a
British
startup
twist.
Cooking
up
a
proper
banger
for
you.
Check
this
out.
好的，我就给大家展示到这里。如果大家不会德语，那很抱歉，不过非常感谢大家。感谢各位。
英文原文
Allright,
I'll
I'll
leave
you
with
that.
If
you
don't
speak
German,
sorry,
but
thanks
so
much.
Appreciate
y'all.
完全不用客气。
英文原文
Noworries
at
噢，对了，如果大家想要幻灯片，我可以倒回去。所有链接都在里面。如果这有帮助的话，大家可以直接在那里获取。太棒了，谢谢大家。祝大家享受接下来的会议。也特别感谢我们后方负责音频的朋友们，没有他们这一切都不可能实现。干杯！
英文原文
Oh,yeah,
and
if
you
want
the
slides,
I
can
just
rewind.
There's
like
all
the
links
in
there.
If
that
If
that's
helpful,
you
can
you
can
just
grab
them
there.
Awesome.
Thank
you.
And
yeah,
enjoy
the
rest
of
the
conference.
And
big
thank
you
as
well
to
our
friends
in
the
back
on
the
audio,
you
know,
wouldn't
be
possible
without
them.
Cheers.