Tushen ilimi / Wasanni

Images, audio da embeddings

The generators daga app, da kuma gine-gine don search: images, video, tallace-tallace, transcription da embeddings, kowane da aka bayar da kullum daga your balance.

An fassara wannan shafin na inji don dacewa. Asalin Ingilishi shine sigar da ke aiki.

Ƙararrawa Images

Yana samar da daya zuwa hudu hotuna daga wani tambayoyi da ya sa su a lõkacin da suka yi. Yana da samuwa na generators kamar yadda ?image a cikin app.

POST https://nymbot.ai/api/v1/images/generations — ake bukata API key, ko Lightning bayyanar da bukatun.

IDS ya zo daga GET /api/v1/models?type=imageƘananan Generator, @cf/black-forest-labs/flux-1-schnell, yana da kudin wani flat 5 standard credits (50 sats) wani picture. Kowane sauran generator rufe Pro credits a kan wani farashin, tare da yawancin farashin da margins, kamar yadda a Ƙananan. n Wasanni n A yanki da wani generator ba ya yi amfani da shi, kuma ba ya yi amfani da shi. A yanki da wani generator ba ya yi amfani da shi kawai.

resolution ba a yi amfani: kowane generator yana samar da wani size. tare da url, kowane hotuna da aka saita zuwa wani jama'a na Blossom kuma za ka samu da rubutu (da wasu generators kawai ba da wani rubutu na su, wanda aka gabatarwa). Kowane mutum da rubutu zai iya buga shi kuma ba za a iya shigar; duba Yadda za a iya ganin APIƘananan b64_json takardar kebantawa a cikin matsaloli da kuma ba zai zama ba tare da. A takardar kebantawa a data: Url a image_url shi ne sarrafa kamar yadda a Tuntube mu da aka saita zuwa Blossom farko don cewa generator za a iya saita shi; shi ne saukewa a kan idan baƙi ba tare da baƙi.

Idan wasu daga cikin n images faili, za ka samu da waɗannan da aka aiki, suna dace kawai ga waɗannan (plus duk da ba da bauta ba tare da bauta), da kuma nymbot.failed ya ce da yawa da suka faru. Idan dukkan haƙĩƙa, baƙi ya saita 502.

Yanzu

{
  "created": 1790726400,
  "model": "nano-banana",
  "cost": 0.2126,
  "data": [
    {
      "url": "https://blossom.example/5c0e4b7d3a91f2e8...c4.png",
      "content_type": "image/png"
    }
  ],
  "nymbot": { "balance": "pro", "charged_credits": 1.817, "charged_sats": 181.7, "balance_credits": 410.608, "balance_sats": 41060.8 }
}

cURL

curl https://nymbot.ai/api/v1/images/generations \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nano-banana",
    "prompt": "A lighthouse at dusk, oil painting",
    "size": "16:9"
  }'

Python

import os
import requests

res = requests.post(
    "https://nymbot.ai/api/v1/images/generations",
    headers={"Authorization": "Bearer " + os.environ["NYMBOT_API_KEY"]},
    json={"model": "nano-banana", "prompt": "A lighthouse at dusk, oil painting", "size": "16:9"},
)
res.raise_for_status()
print(res.json()["data"][0]["url"])

JavaScript

const res = await fetch("https://nymbot.ai/api/v1/images/generations", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.NYMBOT_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ model: "nano-banana", prompt: "A lighthouse at dusk, oil painting", size: "16:9" }),
});
const body = await res.json();
console.log(body.data[0].url);

Wasanni

Wannan shi ne edit endpoint na OpenAI, don haka OpenAI SDKs ' images.edit aiki kamar yadda yana. Only Pro generators with edit a cikin model list ya samu shi.

POST https://nymbot.ai/api/v1/images/edits — ake bukata API key, ko Lightning bayyanar da bukatunƘungiyoyin Ƙungiyar multipart/form-dataSauke 32 MB.

The image ka saukar da aka duba da shi ne mai kyau-tallace PNG, JPEG, WebP ko GIF, da aka saita a matsayin abin da ya yi, da aka saita a kan wani jama'a Blossom host, saboda generators zaune su saita ta hanyar link. Kula da shi a matsayin jama'a. Idan daidaitacciyar ba tare da ba tare da wani abu, da wani abu da aka saita, da shirye-shirye copy an saitawa. A yanayin yana da wannan al'amuran da a kan generator. Price ne price na generator, wanda ga wasu generators yana hada da wani kudi ga saita image.

Yanzu

{
  "created": 1790726460,
  "model": "nano-banana",
  "cost": 0.2126,
  "data": [{ "b64_json": "iVBORw0KGgoAAAANSUhEUgAA..." }],
  "nymbot": { "balance": "pro", "charged_credits": 1.817, "charged_sats": 181.7, "balance_credits": 408.791, "balance_sats": 40879.1 }
}

cURL

curl https://nymbot.ai/api/v1/images/edits \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -F model=nano-banana \
  -F [email protected] \
  -F prompt="Make it a snowy evening"

Python

import base64, os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

with open("photo.png", "rb") as f:
    result = client.images.edit(model="nano-banana", image=f, prompt="Make it a snowy evening")

with open("edited.png", "wb") as out:
    out.write(base64.b64decode(result.data[0].b64_json))

JavaScript

import fs from "node:fs";
import { writeFile } from "node:fs/promises";
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://nymbot.ai/api/v1", apiKey: process.env.NYMBOT_API_KEY });

const result = await client.images.edit({
  model: "nano-banana",
  image: fs.createReadStream("photo.png"),
  prompt: "Make it a snowy evening",
});
await writeFile("edited.png", Buffer.from(result.data[0].b64_json, "base64"));

Wasanni

A bidiyo yana da minti, don haka ya yi aiki a gaban. Za ka sa shi, za ka samu wani id sa'an nan, da kuma tambaya game da id kafin ya yi. Kowane bidiyo generator ya yi amfani da Pro balance.

POST https://nymbot.ai/api/v1/videos — ake bukata API key, ko Lightning bayyanar da bukatunƘaddamar 202.

The price is fixed when you submit, from the generator, resolution and length, so it is charged from your Pro balance as soon as the provider accepts the job, da kuma nuna a matsayin cost, estimated_cost kuma nymbot. Idan abokan ciniki ya ba da aiki, ba tare da wani abu. Idan yiwuwa ba yaushe a baya, ko ba da clips ba za a iya sauke, kuma abokan ciniki ba ya saukar da shi, yiwuwa za a bayar da wani lokaci, ta atomatik. A yiwuwa wanda yana da yaushe bayan sa'o'i ne ba, kuma ya saukar da yaushe, saboda na yiwuwa da yiwuwa a lokacin da ya samu shi. A yiwuwa ya saukar da kyauta amma ba ya saukar da gaskiya na key.

Sauke (202)

{
  "id": "vid_3e9a51c07b2f4d86e0a1c4f2",
  "object": "video",
  "model": "veo",
  "status": "in_progress",
  "created": 1790726400,
  "seconds": 8,
  "resolution": "1080p",
  "estimated_cost": 3.18,
  "expires_at": 1790812800,
  "cost": 3.18,
  "nymbot": { "balance": "pro", "charged_credits": 31.8, "charged_sats": 3180, "balance_credits": 378.808, "balance_sats": 37880.8 }
}

status Za a fara in_progressko completed tare da video a cikin data a lokacin da generator ya sa shi da sauri.

Sauke a kan video

GET https://nymbot.ai/api/v1/videos/{id} - bukatar key wanda ke da nym wanda ya gabatar da shi. A key wanda ya samu ta cap ba za a iya duba.

Yanzu 202 a lokacin da video ne a yi aiki da 200 a lokacin da shi ne kammala ko ya haifarta. Yadda za a ba da kowane 5 zuwa 10 seconds. Kowane tsari ya ba da shawara da ba da shawara a lokacin da ya ba da shawara; shi ba ya ko da yaushe ga video. A aiki da aka haifar da 24 hours bayan ya gabatar da shi. GET /api/v1/videos lists the key's last 50 jobs kamar yadda {"object": "list", "data": […]}.

Tuntube mu (200)

{
  "id": "vid_3e9a51c07b2f4d86e0a1c4f2",
  "object": "video",
  "model": "veo",
  "status": "completed",
  "created": 1790726400,
  "seconds": 8,
  "resolution": "1080p",
  "estimated_cost": 3.18,
  "expires_at": 1790812800,
  "completed_at": 1790726590,
  "data": { "url": "https://blossom.example/9b41d0c2e7a3f658...1e.mp4", "content_type": "video/mp4" },
  "cost": 3.18,
  "nymbot": { "balance": "pro", "charged_credits": 31.8, "charged_sats": 3180 }
}

status Ya in_progress, completed ko failed. A failed aiki carries error ({"code": "generation_failed", "message": …}); idan shi ne daidaitacce, cost 0 da 0 nymbot Tuntube refunded_credits kuma refunded_sats. Hotuna video ne a kan wani jama'a Blossom shirye-shirye, kamar generated images.

cURL

curl https://nymbot.ai/api/v1/videos \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "veo", "prompt": "Waves rolling onto a beach at sunrise", "duration": 8, "aspect_ratio": "16:9"}'

curl https://nymbot.ai/api/v1/videos/vid_3e9a51c07b2f4d86 \
  -H "Authorization: Bearer $NYMBOT_API_KEY"

Python

import os, time
import requests

headers = {"Authorization": "Bearer " + os.environ["NYMBOT_API_KEY"]}

job = requests.post(
    "https://nymbot.ai/api/v1/videos",
    headers=headers,
    json={"model": "veo", "prompt": "Waves rolling onto a beach at sunrise", "duration": 8, "aspect_ratio": "16:9"},
).json()

while True:
    time.sleep(8)
    status = requests.get("https://nymbot.ai/api/v1/videos/" + job["id"], headers=headers).json()
    if status["status"] in ("completed", "failed"):
        break

print(status["data"]["url"] if status["status"] == "completed" else status["error"])

JavaScript

const headers = {
  "Authorization": "Bearer " + process.env.NYMBOT_API_KEY,
  "Content-Type": "application/json",
};

const job = await (await fetch("https://nymbot.ai/api/v1/videos", {
  method: "POST",
  headers,
  body: JSON.stringify({ model: "veo", prompt: "Waves rolling onto a beach at sunrise", duration: 8, aspect_ratio: "16:9" }),
})).json();

let status;
do {
  await new Promise((r) => setTimeout(r, 8000));
  status = await (await fetch("https://nymbot.ai/api/v1/videos/" + job.id, { headers })).json();
} while (status.status !== "completed" && status.status !== "failed");

console.log(status.status === "completed" ? status.data.url : status.error);

Shafin shafi: Text to Speech

Sauke lissafin lissafi da kuma sauke audio fayil, ba tare da wani link. Yana da OpenAI na tallace-tallace, don haka audio.speech.create a cikin OpenAI SDKs aiki.

POST https://nymbot.ai/api/v1/audio/speech — ake bukata API key, ko Lightning bayyanar da bukatun.

Aura 2 ne Pro, priceed da alama ka ba da. The tsare-tsaren ne audio, tare da wani matsaloli Content-Type• The kudin ne a cikin X-Nymbot-Cost-Sats Header. Idan model na tallace-tallace ba tare, ba tare da wani abu.

Yanzu

HTTP/1.1 200 OK
Content-Type: audio/mpeg
X-Nymbot-Cost-Sats: 4.2
X-Nymbot-Balance-Sats: 41055.6

(audio bytes)

cURL

curl https://nymbot.ai/api/v1/audio/speech \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "aura-2", "voice": "luna", "input": "Your invoice has been paid."}' \
  --output speech.mp3

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

audio = client.audio.speech.create(
    model="aura-2",
    voice="luna",
    input="Your invoice has been paid.",
)
audio.write_to_file("speech.mp3")

JavaScript

import { writeFile } from "node:fs/promises";
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://nymbot.ai/api/v1", apiKey: process.env.NYMBOT_API_KEY });

const audio = await client.audio.speech.create({
  model: "aura-2",
  voice: "luna",
  input: "Your invoice has been paid.",
});
await writeFile("speech.mp3", Buffer.from(await audio.arrayBuffer()));

Audio samfurori da mata

Two public lists for picking a tallace-tallace model and voice, or a transcription model. akwai 41 Aura 2 English speakers da four MeloTTS languages.

GET https://nymbot.ai/api/v1/audio/models Duk da haka, ba za a bukatar key.

GET https://nymbot.ai/api/v1/audio/voices?language=en Duk da haka, ba za a bukatar key.

Tuntube Mu (Voices)

{
  "object": "list",
  "data": [
    { "id": "luna", "name": "Luna", "provider": "deepgram", "model_id": "aura-2", "models": ["aura-2"], "language": "en", "description": "Aura 2 English voice", "gender": "female", "preview_url": null },
    { "id": "en", "name": "MeloTTS English", "provider": "myshell", "model_id": "@cf/myshell-ai/melotts", "models": ["@cf/myshell-ai/melotts", "melotts"], "language": "en", "description": "English (MeloTTS)", "gender": null, "preview_url": null }
  ]
}

Models List Yanzu {"object": "list", "data": {"tts": […], "stt": […]}}Kowane model na tallace-tallace yana ba da farashin, farashin, max_input_chars, response_formats, languages kuma default_voice; transcription model yana ba da alama, max_file_bytes, max_seconds, format da farashin a kan minti.

cURL

curl https://nymbot.ai/api/v1/audio/models
curl "https://nymbot.ai/api/v1/audio/voices?language=en"

Python

import requests

print(requests.get("https://nymbot.ai/api/v1/audio/models").json())
for voice in requests.get("https://nymbot.ai/api/v1/audio/voices", params={"language": "en"}).json()["data"]:
    print(voice["id"], voice["model_id"])

JavaScript

console.log(await (await fetch("https://nymbot.ai/api/v1/audio/models")).json());
const voices = await (await fetch("https://nymbot.ai/api/v1/audio/voices?language=en")).json();
for (const v of voices.data) console.log(v.id, v.model_id);

Shafin shafi: Text

Yi amfani da Whisper. Wannan ne Transcription Endpoint na OpenAI, don haka audio.transcriptions.create Kayan aiki.

POST https://nymbot.ai/api/v1/audio/transcriptions — ake bukata API key, ko Lightning bayyanar da bukatunƘungiyoyin Ƙungiyar multipart/form-data.

Ga WAV, WebM, MP4 da Ogg fayiloli, tsawon da aka saita daga fayiloli kafin wani abu ya yi, don haka wani saita fiye da 30 minti an baƙi a kansa (dangane tare da 3 seconds). A WAV fayil na tsawon yana da samfurin tsawon, kananan da samfurin tsawon. Da tsawon da sauran formats, kamar MP3, ba za a baƙi a kansa, don haka su suna ƙarfi da tsawon: a cikin lowest bitrate Nymbot ya gabatar da, 8 kbps, 30 minti ne 1.8 MB, kuma mai girma fayil a wannan format an baƙi da 413 audio_too_long kafin abin da aka yi aiki. Gida ƙarin saita kamar WAV, WebM, MP4 ko Ogg. Idan Whisper bayanai fiye da 30 minti a kowace lokaci, tambayoyi da aka ba tare da 413 audio_too_long, kuma tun da Whisper ya yi aiki, 30 minti suna karɓar.

Za ka bayar da tsawon audio, saukewa zuwa biyu: mafi tsawon tsawon saukewa daga fayil, tsawon Whisper ra'ayi, da kuma mafi girma na fayil ya yiwuwa, a farashin Per-minute na Whisper tare da na'urorin farashin da marufi, da kuma a karkashin 0.05 credit wani baƙi. Yana da aka bayar daga cikin al'amuran a lokacin da cewa za a iya ƙarƙirar kudin, da daga Pro baƙi; 402 Yana samar da abin da kowane tsabar kudi zai bukatar. A cikin app, transcribing wani tallace-tallace ba za a iya free; a kan API shi ne a kowace lokaci. Idan Whisper ba tare, ba tare da wani abu.

Yanzu

{
  "text": "Your invoice has been paid.",
  "usage": { "type": "duration", "seconds": 3 },
  "nymbot": { "balance": "standard", "charged_credits": 0.05, "charged_sats": 0.5, "balance_credits": 120.35, "balance_sats": 1203.5 }
}

text Sauke lissafin lissafi, srt kuma vtt Back subtitles, kuma verbose_json tambaya lissafi, tsawon lokaci, da aikace-aikace segments. Ga uku wanda ba ne JSON, kudin ne a cikin headers.

cURL

curl https://nymbot.ai/api/v1/audio/transcriptions \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -F [email protected] \
  -F model=whisper \
  -F response_format=json

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

with open("memo.m4a", "rb") as f:
    transcript = client.audio.transcriptions.create(model="whisper", file=f)
print(transcript.text)

JavaScript

import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://nymbot.ai/api/v1", apiKey: process.env.NYMBOT_API_KEY });

const transcript = await client.audio.transcriptions.create({
  model: "whisper",
  file: fs.createReadStream("memo.m4a"),
});
console.log(transcript.text);

Translating tallace-tallace zuwa Ingila

POST https://nymbot.ai/api/v1/audio/translations — ake bukata API key, ko Lightning bayyanar da bukatunƘungiyoyin Ƙungiyar multipart/form-data.

Sama da transcription, tare da samfurin ciki har da language, ƙarfi da farashin, amma lissafi ya zo a cikin Birtaniya ba tare da lissafi. The OpenAI SDKs ya kira shi tare da audio.translations.create.

cURL

curl https://nymbot.ai/api/v1/audio/translations \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -F [email protected] \
  -F model=whisper

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

with open("nota.m4a", "rb") as f:
    translation = client.audio.translations.create(model="whisper", file=f)
print(translation.text)

JavaScript

import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://nymbot.ai/api/v1", apiKey: process.env.NYMBOT_API_KEY });

const translation = await client.audio.translations.create({
  model: "whisper",
  file: fs.createReadStream("nota.m4a"),
});
console.log(translation.text);

Ƙananan

Yadda za a yi text a cikin vectors don search, clustering da deduplication. The models rira a kan Cloudflare da suka yi amfani da kayan aiki.

POST https://nymbot.ai/api/v1/embeddings — ake bukata API key, ko Lightning bayyanar da bukatun.

The list of models is the source of truth for which are available and what they cost; Google's EmbeddingGemma, tare da karshe vectors on request, ya nuna akwai kuma a lokacin da catalog has wani farashin ga shi. Embeddings suna daidaitawa da kowane input token, da kuma 0.05-credit minimums daidaita ga kowane baƙi, ba tare da kowane baƙi, don haka batching da yawa rubutu a cikin wani baƙi ne mafi kyau fiye da sauke su daya a lokaci.

Yanzu

{
  "object": "list",
  "data": [
    { "object": "embedding", "index": 0, "embedding": [0.0213, -0.0487, 0.0112] }
  ],
  "model": "@cf/baai/bge-m3",
  "usage": { "prompt_tokens": 9, "total_tokens": 9 },
  "nymbot": { "balance": "standard", "charged_credits": 0.05, "charged_sats": 0.5, "balance_credits": 1204.35, "balance_sats": 12043.5 }
}

cURL

curl https://nymbot.ai/api/v1/embeddings \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "@cf/baai/bge-m3", "input": ["Lightning invoices expire.", "Invoices on Lightning have a time limit."]}'

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

result = client.embeddings.create(
    model="@cf/baai/bge-m3",
    input=["Lightning invoices expire.", "Invoices on Lightning have a time limit."],
)
print(len(result.data), len(result.data[0].embedding))

JavaScript

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://nymbot.ai/api/v1", apiKey: process.env.NYMBOT_API_KEY });

const result = await client.embeddings.create({
  model: "@cf/baai/bge-m3",
  input: ["Lightning invoices expire.", "Invoices on Lightning have a time limit."],
});
console.log(result.data.length, result.data[0].embedding.length);