Motheo oa tsebo / Baetsi ba lenaneo

Litšoantšo, molodi le embeddings

Lisebelisoa tsa ho bōpa (generators) tse tsoang lenaneong (app), le lisebelisoa tsa motheo tsa ho batlisisa: litšoantšo, video, puo, ho ngola mantsoe a builoeng le embeddings, e ’ngoe le e ’ngoe e lefelloa ka phelisano ea eona ho tsoa bolokong ba hau.

Leqephe lena le fetoletsoe ka mochini hore le be bonolo. Phetolelo ea mantlha ea Senyesemane ke eona e sebetsang.

Ho hlahisa litšoantšo

E etsa litšoantšo tse le tše kae ho tloha ho taelo 'me e li khutlisetsa ha li se li qetile. Ke sehlopha se le se le feleng sa lisebelisoa tsa ho bōpa tsa ?image ka har'a app.

POST https://nymbot.ai/api/v1/images/generations — e hloka API key, kapa lefu la Lightning ka kopo kaofela.

Li-ID li tsoa kae GET /api/v1/models?type=image. Sehlahiso-motlakase se tloaelehileng, @cf/black-forest-labs/flux-1-schnell, e qeta litshelete tse 5 tsa mantlha (50 sats) ka senepe kaofela. Generator e mong le e mong o sebelisa litshelete tsa Pro ka tlhaho ea oona, ka tefo le mokoloko o tloaelehileng, joalo ka lenaneo. n litšoantšo li cost n ho feta hoo. Letšema leo generator e le sa le amoheleng le latlhotsoa ho e-na le ho hana; generator ea tloaelehileng e sebelisa lenwhatlo feela.

resolution ha e sebelisoe: generator e ’ngoe le e ’ngoe e etsa boholo ba eona. Ka url, sontlha ka senepe ka senepe se tsoaloa ho Blossom host e khutsanyane mme o fumana konokono ea sona (makenika a se ke a fana ka konokono ea bona feela, e eang pele). Motho e mong le e mong ea nang le konokono a ka se bula mme ha e ke ea nkuoa hape; bona API e ka bona eng. Le b64_json setšoantšo se khutlela moralo e bile ha se hanngoe se hloletswe. Setšoantšo se rometsoeng e le a data: URL ka image_url na e hlahloboa ka tsela e tšoanang le e fetola mme e ne e ka hloelletsoe Blossom pele hore generator e e khone ho e hloella; e hlakolloa hape haeba kopo e sitoa ntle le tefo.

Haeba ba bang ba n lifoto li hloleha, o fumana tseo li sebetseng, o lefelloa feela ka tseo (le tseo mofumahali a li lefetseng le ha li hloleha), le nymbot.failed ho bolela hore ho le mengata ha e teng. Haeba bohle ba hlōla, kopo e khutla 502.

Karabo

{
  "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);

Ho lokisa litšoantšo

Ho fetola seswantsho seo u se rometseng, ho latela taelo. Sena ke sebaka sa ho fetola sa OpenAI, kahoo SDK tsa OpenAI... images.edit se sebetsa jwalokaha e le jalo. Ke ba hlahisoa ba Pro feela le edit lepepisi ea limodela amohela eona.

POST https://nymbot.ai/api/v1/images/edits — e hloka API key, kapa lefu la Lightning ka kopo kaofelaMmele ke multipart/form-data, ho fihla ho 32 MB.

Setšoantšo seo u se kenyesang se hlahloboa ho netefatsa hore ke PNG, JPEG, WebP kapa GIF e lokileng, e rometsoeng ka mofuta oa eona oa nnete, 'me se beiloe holim'a moshini oa Blossom oa sechaba, hobane lisebelisoa tsa ho bōpa li nka lintlha tsa tsona ka litemoso (links). Se kōpelo tšoane le ea sechaba. Ha ho sa tsamaee hantle mme ho se tlatsoe letho, khophi e behiloeng e hlakolosoa hape. Karabo e na le sebopeho se tšoanang le sa ho bōpa. Litšenyehelo ke tša moshini oa ho bōpa, tseo ho ba bang ba tšoanang li kenyelletsang tefo ea setšoantšo se kenyesetsoeng.

Karabo

{
  "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"));

Video

Video e nka metsotso, kahoo e sebetsa ka morao. O e romela, o fumana id hang-hang, mme o botsa ka id ho fihlela e qetile. Mofuta o mong le o mong oa ho bōpa video o senya chelete ea Pro.

POST https://nymbot.ai/api/v1/videos — e hloka API key, kapa lefu la Lightning ka kopo kaofela. Ho khutla 202.

Ntlao e tiisitswe ha o romela, ho tloha ho generator, resolution le []lelelele, kahoo e ntlafatsa balance ea hau ea Pro hanger kapele ha mofahi a amohela mosebetsi, mme e bontšoa e le cost, estimated_cost le nymbotHa mothusi a hana mosebetsi, ha ho boloetsoe letho. Ha ho rhenrwang (render) ha hloleha hamorao, kapa video e phethehileng e se e ke ea bolokoa mme mothusi a sa e kofolle, tefo e khutlisetsoa morao ka leeto, ka boiketsetso. Ho rhenra ho ntseng ho ntse ho tsamaea ka mor'a nako e le hahora ho emisoa, mme tefo ea sona e lula e le teng, hobane mothusi o kofollela ho rhenra hang ha a se amohela. Ho khutlisetsoa tefo ho khutlisetsa lintlha (credits) morao empa ha ho fokise palo ea litšenyehelo tsa konokono.

Karabo (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 e qala e le in_progress, kapa completed ka video e se e le ka hare data ha generator e khutlile hang-hang.

Ke hlahloba video

GET https://nymbot.ai/api/v1/videos/{id} — e hloka senotlolo se le belonging ho nym e e nepahetseng. Senotlolo se fihlletseng sechapa se ka ntse sa hlahloba.

E araba 202 ha video e ntse e etsoa le 200 hang ha e felile kapa e hlolehile. Botsa nako le nako ka metsotso e 5 ho isa ho ea 10. Tlhahlobo e 'ngoe le e 'ngoe e botsa mofaki ka lilemo tse le 'ngoe ebe e araba hang-hang; ha e emele video nako e telele. Mosebetsi o lula o bolokehiloe ka lihora tse 24 ka mor'a hore o ne o nepahetsoe. GET /api/v1/videos fana ka mesebetsi ea ho qetela ea 50 ea kae ea senotlolo e le {"object": "list", "data": […]}.

Karabo (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 ke in_progress, completed kapa failed. A mosebetsi o sosobetseng o na le error ({"code": "generation_failed", "message": …}); eba ne e khutlisetsoe, cost na 0 le nymbot o eketsa refunded_credits le refunded_satsVideo e felletseng e holim'a Blossom host e pepetsoang, joalo ka litšoantšo tse hlahisitsoeng.

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);

Ho fetolela mongolo hore e be lentsoe

O bala mongolo ka lentsoe ebe o kenya sesebelisoa sa lentswe ka boyona, eseng khoutu (link). Ke sesebelisoa sa OpenAI sa puo, kahoo audio.speech.create ka di-OpenAI SDKs ho sebetsa.

POST https://nymbot.ai/api/v1/audio/speech — e hloka API key, kapa lefu la Lightning ka kopo kaofela.

Lentswe la mofuta o tloaelehileng le lefelloa ka li-credit tse 3 tse tloaelehileng (30 sats) ka kopo, jwaloka ka thahaseng. Aura 2 ke Pro, e lefelloang ka litakhahlo letlhako tseo u li romelang. Karolo ya karabo ke lentswe, e nang le tsamaia e lekanang Content-Type; theko e ka har'a X-Nymbot-Cost-Sats lekhala. Haeba modeli ea puo e sitoa, ha ho ketsoe tefo.

Karabo

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()));

Mekahlelo ea molumo le lipitso

Liphahlo e tharo tsa sechaba tsa ho khetha mofuta oa puo le lentsoe, kapa mofuta oa ho ngola mantsoe a builoeng. Ho na le 41 ba buang ka Senyesemane ba Aura 2 le lipuo tse nne tsa MeloTTS.

GET https://nymbot.ai/api/v1/audio/models — ha ho hloke kofutši.

GET https://nymbot.ai/api/v1/audio/voices?language=en — ha ho hloke kofutši.

Karabo (mantsoe)

{
  "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 }
  ]
}

Lentokotlo la mahlale le araba litharollo {"object": "list", "data": {"tts": […], "stt": […]}}. Mofuta e mong le e mong oa puo o fana ka leemo la oona, tlhaho, nako, max_input_chars, response_formats, languages le default_voice; mohlala oa ho ngola o fana ka mabitso aona a mang, max_file_bytes, max_seconds, mefuta le tšhelete ea metsotso e le nngwe.

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);

Puiso ho becomela mongolo

E fetolela rekoto mongolo ka Whisper. Sena ke transcription endpoint ea OpenAI, kahoo audio.transcriptions.create ea sebetsa.

POST https://nymbot.ai/api/v1/audio/transcriptions — e hloka API key, kapa lefu la Lightning ka kopo kaofelaMmele ke multipart/form-data.

Bakeng kahoo lifaele tsa WAV, WebM, MP4 le Ogg, nako e baloa ho tsoa lifaele tsa tsona pele ho qala ntho efe kapa efe, kahoo pheta-pheta e feta metsotso e 30 e hanyetsoa hona hona (ka metsotso e 3 ea mohlaomeli). Nako ea faele ea WAV e tsoa rate ea sample, likanala le boholo ba sample. Nako ea mafomata a mang, joalo ka MP3, ha e khonehe ho baloa hona hona, kahoo a bontšoa ka boholo: ka bitrate e tlase haholo eo Nymbot e e ipona e le 8 kbps, metsotso e 30 ke 1.8 MB, mme faele e kholo ka mofuta o joalo e hanyetsoa ka 413 audio_too_long pele ntho efe kapa efe e qala. Romela liphetolelo tse telele e le WAV, WebM, MP4 kapa Ogg. Haeba Whisper e bontša hore na ho na le metsotso e fetang 30 leha ho le joalo, kopo e latoloa ka 413 audio_too_long, mme kaha Whisper e tsamaetse, metsotso e 30 e lefisiwa.

U lefa ka nako ea lere (audio), u ronkela ho fihla ho sekondi: nako e telele ka ho fetisisa ea nako e baliloeng ho tsoa ka fikele, nako eo Whisper e e lipotsang, le nako e nyenyane ka ho fetisisa eo boholo ba fikele bo e lumellang, ka tlhahloho ea tefo ea Whisper ea metsotso ka metsotso le tefo ea tloaelehileng le margin, le ka bongata bo ka bang 0.05 credit ka kopo. Ho lefeloa ho tsoa ka balansi ea tloaelehileng haeba e ka khona ho lefa tefo eo, haeba ho le tsela e ’ngoe ho lebeloa ho tsoa ho Pro; a 402 ho bontša se e mong le e mong ea li-balance a hlokang. Ka har'a app, ho fetolela molaetsa oa lentsoe ho ka ba mahala; ka API ho nkuoa tefo ka nako tsohle. Haeba Whisper e hlolehile, ha ho nkuoe tefo efe kapa efe.

Karabo

{
  "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 o khutlisetsa molaetsa o sa na le tlhaku tse tloaelehileng, srt le vtt khutlisetsa litlhaloso, le verbose_json o kenyelletsa puo, nako le likarolo tse nang le nako. Bakeng sa tse tharo tse seng JSON, molalefatso o fumaneha lihloohong tsa mangolo.

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);

Ho fetolela puo ho English

POST https://nymbot.ai/api/v1/audio/translations — e hloka API key, kapa lefu la Lightning ka kopo kaofelaMmele ke multipart/form-data.

Joalo ka ho ngola molumo, ka melaetsa e tšoanang NTLA ntle le language, meeli le tahaloso ea litlhahloebiso, empa mongolo o khutla ka Senyesemane ho sa tsotellehe puo e ileng ea buuoa. OpenAI SDKs li e bitsoa ka 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);

Embeddings

E fetola mongolo hore e be li-vector bakeng sa ho batlisisa, ho kopanya, le ho tlosa lintlha tse phelang ka ntho e le ngoe. Lioelelo (models) li sebetsa ho Cloudflare 'me li sebelisa chelete e tloaelehileng.

POST https://nymbot.ai/api/v1/embeddings — e hloka API key, kapa lefu la Lightning ka kopo kaofela.

Lenalanana la dimodela ke mohloli oa nnete mabapi le hore na ke efe e teng le hore na li teka bokae; EmbeddingGemma ea Google, e nang le di-vector tse khutšoanyane ha ho kopa, e hona le hona e bonahala teng ha lenaneo le na le telo bakeng sa yona. Di-embedding li lekantsoe ka token ea mofuta (input token), 'me molaeto oa 0.05-credit o sebelisoa ka kopo e 'ngoe le e 'ngoe, eseng ka mofuta o 'ngoe le o 'ngoe, kahoo ho kopanya litemana tse ngata ho etsa kopo e 'ngoe ho tloaela ho le bobebe ho feta ho li romela ka nako e 'ngoe le e 'ngoe.

Karabo

{
  "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);