Cloudflare Developers•2mo ago

Hello, do you have any intention to offer text to speech services as a websocket / other formats apa

Hello, do you have any intention to offer text to speech services as a websocket / other formats apart from mpeg?

TTim Hello, do you have any intention to offer text to speech services as a websocket...

samjs•11/4/25, 9:57 PM

I believe aura-2 supports websockets: https://developers.cloudflare.com/workers-ai/models/aura-2-en/

CCelestial Rose Agreed! I also found that the images within a pdf dont get OCR'd. They're being ...

Celestial Rose•11/4/25, 10:00 PM

Any update ?

TimOP•11/4/25, 10:02 PM

I tried aura-2 yesterday for websockets, using the websocket: true option, but it didn't return a websocket

TimOP•11/4/25, 10:07 PM

I'll try again and see that I'm not crazy

yinxingmaiming6409•11/5/25, 5:32 AM

It seems that many interfaces are not fully compatible with OpenAI

yinxingmaiming6409•11/5/25, 5:32 AM

Hope to integrate into the qwen3-vl model

Aiden•11/5/25, 8:29 PM

Anyone else getting AiError 9002 today? Seems to be a service issue

Aiden•11/5/25, 11:04 PM

Looks like specifically editing vector DBs where we get the 9002 internal error

DRPower•11/6/25, 3:25 AM

Hello everyone, I am trying to figure out how to fix the following deploy error from Cloudflare VibeSDK, I keep getting the following error "▲ [WARNING] You are about to publish a Workers Service that was last published via the Cloudflare Dashboard.
10:18:17.676
10:18:17.676 Edits that have been made via the dashboard will be overridden by your local code and config.
10:18:17.676
10:18:17.676
10:18:17.676 ✘ [ERROR] A request to the Cloudflare API (/accounts/44488d79973a81689876492e372fe199/workers/scripts/october-vibesdk) failed.
10:18:17.677
10:18:17.677 Cannot apply new-class migration to class 'DORateLimitStore' that is already depended on by existing Durable Objects [code: 10074]
10:18:17.677
10:18:17.677 If you think this is a bug, please open an issue at: https://github.com/cloudflare/workers-sdk/issues/new/choose
10:18:17.678
10:18:17.678
10:18:17.678

Logs were written to "/opt/buildhome/.config/.wrangler/logs/wrangler-2025-11-05_15-18-11_223.log"
10:18:17.678
10:18:17.681 error: script "deploy" exited with code 1
10:18:17.684 Failed: error occurred while running deploy command"

GitHub

Build software better, together

GitHub is where people build software. More than 150 million people use GitHub to discover, fork, and contribute to over 420 million projects.

zsueo•11/6/25, 12:51 PM

Are there any plans for open sourcing Omni? I would love to contribute if that is possible

Celestial Rose•11/6/25, 3:56 PM

https://developers.cloudflare.com/workers-ai/models/llama-4-scout-17b-16e-instruct/ hey! for llama4 type here could be

text

text

image_url

image_url

but the type is simply

string

string

, could be more insightful with a union type

Capture_decran_2025-11-06_a_17.55.58.png

Cloudflare Docs

llama-4-scout-17b-16e-instruct

Meta's Llama 4 Scout is a 17 billion parameter model with 16 experts that is natively multimodal. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.

Celestial Rose•11/6/25, 4:31 PM

Experimenting with llama-4-scout in Workers AI, the model stops abruptly almost 100% of the time and doesn't finish its reply in a single message chat using env.AI.
Do we know if its a momentary issue ? Anyone experienced that ?

CCelestial Rose Experimenting with llama-4-scout in Workers AI, the model stops abruptly almost ...

Celestial Rose•11/6/25, 4:32 PM

both in stream mode and not. stream sends a DONE before the end of the chat, its not the worker failing

itspauv•11/6/25, 7:18 PM

hey, any chance we will get the new DeepSeek OCR model? (or any other OCR model for that matter)

yinxingmaiming6409•11/8/25, 1:22 PM

Does anyone know? When can he support qwen3-vl

Jadu•11/8/25, 5:12 PM

@SuperHelpflare can you help em with an ai diccument writer i am getting error in it

Jadu•11/8/25, 5:13 PM

@SuperHelpflare

Jadu•11/8/25, 5:13 PM

why isnt it working

Celestial Rose•11/8/25, 9:39 PM

Opened a PR for Llama4 images to work for the AI SDK https://github.com/cloudflare/ai/pull/303
This follows the documentation found herehttps://developers.cloudflare.com/workers-ai/models/llama-4-scout-17b-16e-instruct/

GitHub

Add support for base64 images in chat messages by celestial-rose ·...

Handle base64 image data for Llama 4 in chat messages.
As per the documentation found here https://developers.cloudflare.com/workers-ai/models/llama-4-scout-17b-16e-instruct/

Cloudflare Docs

llama-4-scout-17b-16e-instruct

CCelestial Rose Opened a PR for Llama4 images to work for the AI SDK https://github.com/cloudfla...

Celestial Rose•11/8/25, 9:55 PM

forgot i had to also change the "text" case so it outputs an object for it to work. put it to draft; wondering how to adapt without breaking anything. the inputs needs to have

"type": "text"

"type": "text"

Andrew Hansen•11/9/25, 3:53 AM

Is there a plan to make GPU’s available to host custom models on someday? We have a custom model we are integrating currently

TimOP•11/9/25, 9:49 PM

Morning from the land down under.

I'm attempting to use Flux again (I was using Deepgrams) - I am noticing their platform is more performative.

But, I'm having an issue where Flux appears to die. I'm not receiving any errors - but the Cloudflare instance accepts a couple of audio chunks, then appears to close the connection.

Here's the request ID: Flux connection confirmed { requestId: '616f1c9e-ab87-4942-9992-1a23dac29cab' }

Here's some logs, to see what happened:

[DEBUG][SpeechToTextOrchestrator] Handling end_of_turn { turnIndex: 0, transcript: 'Hi. How are you?' }
[DEBUG][TranscriptBuffer] No buffered content, content unchanged
[DEBUG][SpeechToTextOrchestrator] Processing new request { reason: 'first turn' }
[DEBUG][PendingMessageReconciler] Starting reconciliation { pendingMessagesCount: 1, newTranscript: 'Hi. How are you?' }
[DEBUG][SpeechToTextOrchestrator] Reconciled turn info {
originalTranscript: 'Hi. How are you?',
originalWordsCount: 4,
reconciledTranscript: 'Hi. How are you?',
reconciledWordsCount: 4,
pendingMessagesCount: 1
}
[DEBUG][TranscriptBuffer] Buffered turn info { turnIndex: 0, transcript: 'Hi. How are you?' }

[DEBUG][LangModelOrchestrator] Language model request completed for 1762724680932_bwfrjit { contentLength: 131, toolCallCount: 0 }
[DEBUG][TranscriptBuffer] Clearing buffer
[DEBUG][SpeechToTextOrchestrator] Handling end_of_turn { turnIndex: 1, transcript: 'Can you count to ten?' }
[DEBUG][TranscriptBuffer] No buffered content, content unchanged
[DEBUG][SpeechToTextOrchestrator] Processing new request { reason: 'first turn' }
[DEBUG][TranscriptBuffer] Clearing buffer
[INFO][RequestManager] Created new request 1762724692649_tfpk167
[DEBUG][CloudflareFlux] Flux WebSocket connection closed

This conenction closed at the end, was not me hanging up. It just did that itself. I don't have any errors or exceptions showing.

CCelestial Rose forgot i had to also change the "text" case so it outputs an object for it to wo...

Celestial Rose•11/10/25, 2:36 PM

perhaps even the type text should be default if no type is set

Celestial Rose•11/10/25, 3:51 PM

is it planned to add a AI Search (AutoRAG) parameter to the createWorkersAI of the Vercel AI SDK
https://developers.cloudflare.com/workers-ai/configuration/ai-sdk/
so we can init the binding with a autorag param ?

Cloudflare Docs

Vercel AI SDK

Workers AI can be used with the Vercel AI SDK for JavaScript and TypeScript codebases.

Celestial Rose•11/10/25, 3:54 PM

the same way we have "gateway"

Celestial Rose•11/10/25, 3:58 PM

oh wow, just found in the package a "createAutoRAG" instead of createWorkersAI which is a completely undocumented api, !

Celestial Rose•11/10/25, 4:09 PM

hmm its a bit weird, the generation model is hardcoded and is not using the model in the options, is it a non-released API on purpose ?

CCelestial Rose forgot i had to also change the "text" case so it outputs an object for it to wo...

Celestial Rose•11/10/25, 4:43 PM

funnily enough, returning an object instead of a string made me discover that it breaks the

const query = messages.map(({ content, role }) =>

const query = messages.map(({ content, role }) =>

${role}: ${content}

).join("\n\n");

).join("\n\n");

helper for the AutoRAG prompt system. also this is repeated itself twice and deserve a function on its own. will fix the PR for the base64 images and add it all there

Fernando•11/11/25, 8:03 AM

Deepseek OCR please

Celestial Rose•11/11/25, 8:21 AM

https://tenor.com/view/what-huh-confused-john-travolta-gif-16946746

Tenor

Celestial Rose•11/12/25, 8:58 AM

Hey ! Would be nice to add to the "Capability" to the Models page to filter by multimodal, image input, OpenAI Repsonses API etc etc

Capture_decran_2025-11-12_a_10.58.14.png

Celestial Rose•11/12/25, 1:17 PM

There's a bug in the autorag AI Binding where the totalUsage is always zero in stream mode when we reach the "finish" part

Celestial Rose•11/12/25, 1:17 PM

it does work with regular AI binding

blah•11/12/25, 3:02 PM

Requesting help with my community help request: "Request AI Streaming Binding Access". Can't post the link :(.

Issue is that this toy request (as well as my real ones) fail to return stream body:

export default {
async fetch(req, env) {
const model = “@cf/meta/llama-2-7b-chat-int8”;
const response = await env.DOCTALK_AI.run(model, {
prompt: “What is a tomato?”,
stream: true,
});
console.log(“response:”, response);
return new Response(response.body ? “

Stream OK” : “

No stream body”, {
status: 200,
});
},
};

No stream body
“[Worker] AI error: Error: No stream body returned”

any assistance greatly appreciated!!!

Bblah Requesting help with my community help request: "Request AI Streaming Binding Ac...

Celestial Rose•11/12/25, 5:50 PM

You shouldn’t do response.body
Streams don’t use body

Bblah Requesting help with my community help request: "Request AI Streaming Binding Ac...

Celestial Rose•11/12/25, 5:50 PM

heres the doc https://developers.cloudflare.com/workers-ai/configuration/bindings/#methods

Cloudflare Docs

Workers Bindings

Workers provides a serverless execution environment that allows you to create new applications or augment existing ones.

CCelestial Rose heres the doc https://developers.cloudflare.com/workers-ai/configuration/binding...

blah•11/12/25, 6:20 PM

Thank you!

Paul•11/13/25, 4:21 PM

Hi, wanted to ask the community here if there is a combination you find works well together of a Agentic Code CLI and a Model from Workers AI specifically. If your familiar with Claude Code, that's what I'm trying to determine if I could build a lower cost cloudflare based version of. Ideas?

PPaul Hi, wanted to ask the community here if there is a combination you find works we...

Paul•11/13/25, 4:25 PM

For example I tried combining Aider CLI with Amazon Nova (Not on cloudflare, just an example), and now I'm wonder if I can do the same with Cloudflare hotsed models? - BTW the Aider/Nova combination isn't working too well for me so far

PhoenixSpace•11/13/25, 4:25 PM

IME the cloudflare hosted models tend to be a bit more expensive then other providers. If you want low latency/edge usage, it's great, but if pure cost is your benchmark then other providers will get you a bit better pricing

PPhoenixSpace IME the cloudflare hosted models tend to be a bit more expensive then other prov...

Paul•11/13/25, 4:25 PM

Ok, thanks for the insight. I guess I didn't do a cost analysis, for some reason I sort of assumed they would be cheaper on cloudflare

like most stuff

PhoenixSpace•11/13/25, 4:28 PM

If you need to scale and run AI stuff globally/on the edge, their pricing is fantastic. If it’s just a single user internal tool, there are slightly cheaper options

Paul•11/13/25, 4:29 PM

I need to get my head around "Neurons" pricing - so I can comapre apples to apples with other solutions.

PhoenixSpace•11/13/25, 4:30 PM

The model pages usually have price per M tokens

PhoenixSpace•11/13/25, 4:30 PM

https://developers.cloudflare.com/workers-ai/models/gpt-oss-120b/

Cloudflare Docs

gpt-oss-120b

OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases – gpt-oss-120b is for production, general purpose, high reasoning use-cases.

Brick_Syntax•11/13/25, 9:52 PM

Hey! so According to chat gpt I can use worker AIs to make my self a AI api, but it says there is limit, it said something about 10,00 neurons per day, now I wanted a better source so is this true? and if so how many neurons per task?

boke0•11/15/25, 12:45 AM

Hi there, I could use some help.
A few days ago, my product, which is built on Cloudflare Workers and integrates with Workers AI (GPT-OSS-120b) through bindings, broke because the interface changed (prompt_tokensprompt_tokens and completion_tokenscompletion_tokens were replaced with input_tokensinput_tokens and output_tokensoutput_tokens).
And today, I ran into another issue: the instructionsinstructions parameter stopped working when the input was in an OpenAI-like format (like [{role: "assistant", content: "foobar" }, ...][{role: "assistant", content: "foobar" }, ...]).

Where can I check for these kinds of interface changes in advance so I can update my product before it breaks?

bayes•11/15/25, 8:41 PM

did someone tested deepgram's nova-3 in workers ai with diarization? always getting timeout regardless of file size or type

KZ•11/16/25, 8:13 PM

is there a channel that has the ball on web-bot-auth specifically the http message signature (9421) is that this group or agents or some other?

Hello, do you have any intention to offer text to speech services as a websocket / other formats apa

Similar Threads

Similar Threads

Similar Threads