Speech is now in Beta. Try the first model ever that creates spoken audio with matching background music. Update your app for the latest. Read more here:

Speech can say things like the Sirens passage from the Odyssey in Gen Z slang.

Or plead with your roommate to do the dishes in Victorian English.

Try Speech today. Now in Beta, only on Suno. (And beta really means beta. Sometimes British accents may sound more Australian or dramatic pauses may be veryyyy dramatic. This will improve over time.)

Suno Speech + Opus 5.5 = love note making perfection

speech + background music in one pass is the kind of thing that sounds trivial until you try to keep them temporally coherent. two generators fighting for the same timeline usually smear each other. if the music actually ducks, swells, and punctuates around the voice instead of being glued on after, that's a real step for realtime audio.

When are we getting a better (i.e. older) model so we can get on with making music?

Speech doesn’t feel right to me as the name for this. What about Vocal Booth?

楽しい機能をありがとうございます。Speechでもマイボイスを使えたらもっと嬉しいので、マイボイスを使えるようにしてもらえると、もっと楽しめると思うから、開発して貰いたいです。 いつも楽しませて貰ってありがとうございます😊

finally, AI audiobooks with a dramatic soundtrack nobody asked for

No

OH NOOO!!! IT COUNTS TO DOWNLOAD LIMITS??!

Looks like a fun feature! Voice implementation would be highly appreciated. Otherwise than that first tests sound promising. Oh maybe a style section if bgm is activated?

I would like to speak a line or lines and have the AI voice tweak my audio so I can do all the acting in videos I make because real actors are ass. Is there a way to do that?

Could this make AI generated stories feel more alive?

Duni speeched before it was cool.

🥳🎉❤️

It needs MAJOR improvement. In a brief test using Brazilian Portuguese, it exhibited several issues—such as massive pauses and switching to European Portuguese mid-sentence—in addition to producing bizarre, indescribable sounds.

I can finally stop importing my dramatic elevenlabs vocals?

Love it! This is what I want to say about it:

We’ve had to build ‘workarounds’ for this. Excited to see it as a native feature!!!

Spoken audio with a bed that locks under it is a podcast intro and a trailer VO in one pass. Curious how clean that speech stem exports when you mute the music.

@upchartofficial Was trying to teach it Geordie - northern English the other day but failed lol

You nerfed my existing annual subscription. How about a refund?

Gave it a try, I like that you can isolate spoken audio or combine it with background music as well.

Suno Speech ™

Ok @suno but does 1 speech download means burning one of our 15 monthly allowed download like you do for SOUNDFX ? Seriously ? 15 downloads of SOUNDFX per month?

Ich find es wichtig das ihr mehr Optionen gibt für die Stimme mehr nach der originalen Stimme zu klingen. Das ist das einzige was meine Lieder neben den eigenen Texten, zu mir macht. ✌🏻 Danke für die Anpassungen der Stimme bei v. 6. Und entschuldigt bitte den wütenden Song ❤️‍🩹

I've been doing this for a long while already. Nice.

Does that mean you are using elevenlabs v4 😑

I gave it a shot and I can create better spoken tracks in Music. the speech not so great...

I had a dream! (Please set it to drum and bass music with African horns)

Stoked to start playing around with this

wow, sounds terrible

But can you use your own voice models with Speech?

日本語はいけるのかしら？

Your models can already do speech well if you prompt properly, is this just a smaller model then?