Any Plans to Add Voices Like Juniper to the Realtime API?

API Feedback
,
1

Hi OpenAI team,

I’m wondering if there are any plans to add more voices—like Juniper from the ChatGPT app—to the Realtime API.

Currently, the Realtime API offers a solid set of voices: Alloy, Echo, Fable, Onyx, Nova, Shimmer, Ash, and Ballad. However, some of the more expressive and natural-sounding voices from the ChatGPT mobile experience (like Juniper, Sky, and Cove) are not yet available through the API.

Juniper in particular stands out for its clarity and personality, and I’d love to see it (and other similar voices) available for low-latency applications via the API. I haven’t seen any announcements regarding this, so I figured it couldn’t hurt to ask.

Is there any plan to expand the Realtime API voice options to include these?

Thanks,

Suren Kocharian

6 Likes
2

Thanks for your post, Suren.
I’m adding my scenario as well by commenting on your post.

Hi, OpenAI team,

I didn’t expect this to be an issue, but in real-time applications (such as Twilio), using a robotic voice—especially one with pitch or mood changes—is not well-received in real-world usage scenarios. Testers provided feedback noting that the voice sounded inconsistent, and some felt as though the speaker (AI) changed mid-conversation due to the shifting tone or pitch. This created a sense of disconnection and reduced the overall user experience.

I hope to see some improvements in the real-time API regarding this.

Thank you.

1 Like
3

Hi OpenAI team,

I’m wondering if there are any plans to add more voices—like Juniper from the ChatGPT app—to the Realtime API.

Currently, the Realtime API offers a solid set of voices: Alloy, Echo, Fable, Onyx, Nova, Shimmer, Ash, and Ballad. However, some of the more expressive and natural-sounding voices from the ChatGPT mobile experience (like Juniper, Sky, and Cove) are not yet available through the API.

Juniper in particular stands out for its clarity and personality, and I’d love to see it (and other similar voices) available for low-latency applications via the API. I haven’t seen any announcements regarding this, so I figured it couldn’t hurt to ask.

Is there any plan to expand the Realtime API voice options to include these?

Thanks,

**Sean Fletcher

P.S this is really annoying why you wouldn’t allow Web/Mobile UI voices in the API seems backwards if they are good enough for public normal use us developers should be able to use them**