Isisekelo solwazi Izinzuzo
Images, audio kanye embedments
I-generators kusuka ku-app, ne-building blocks yokufunda: izithombe, i-video, i-speech, i-transcription kanye ne-embeddings, zonke zithunyelwe ukusetshenziswa kwebhizinisi yakho.
Leli khasi lihunyushwe ngomshini ukuze kube lula. IsiNgisi sangempela inguqulo esebenzayo.
Ukwenza Images
Yenza isithombe 1 kuya 4 kusuka ku-prompt futhi ivumela ngemuva kokwenza. It is the same set of generators as ?image Ngaphandle kwe-app
POST https://nymbot.ai/api/v1/images/generations — unemibuzo ye-API, noma I-Lightning Payment ngesicelo.
Izithombe ezivela GET /api/v1/models?type=imageI-Generator ye-Generator ye-Generator
@cf/black-forest-labs/flux-1-schnell, izindleko flat 5 amayunithi standard (50 sats) isithombe. Wonke ezinye generator isithombe amayunithi Pro ngentengo yayo, nge izindleko ezivamile futhi margin, njengoba ku Ngena ngemvume. n Izindleko ze-images
n I-field eyenziwe ngama-generator iyahlekile ngokufakelwa; i-generator ye-standard isebenzisa kuphela i-prompt.
| isikhunta | Uhlobo | Ukubalwa | Ukucaciswa |
|---|---|---|---|
model | Ukuhlobisa | Yebo | I-Generator ID, njenge nano-banana. |
prompt | Ukuhlobisa | Yebo | Yini ukuyifaka. Kunzima kuphela izici ezingu-2000 ezidlulileyo. |
n | Ngena ngemvume | Ngaphandle | I-1 kuya ku-4 I-Default 1. Isetshenziswa nangokuthi num_images. |
size | Ukuhlobisa | Ngaphandle | I-Aspect Ratio efana ne- "16:9", noma i-OpenAI usayizi efana "1792x1024", okuyinto enhle kakhulu 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9, 5:4 futhi 4:5. "auto" Hlola ku generator. |
aspect_ratio | Ukuhlobisa | Ngaphandle | Imininingwane size, futhi wahlanganyela uma amabili zithunyelwe. |
quality | Ukuhlobisa | Ngaphandle | Generator-specific, njenge "low", "medium" noma "high". |
negative_prompt | Ukuhlobisa | Ngaphandle | Yini ukugcina. |
output_format | Ukuhlobisa | Ngaphandle | "png", "jpeg" noma "webp". |
response_format | Ukuhlobisa | Ngaphandle | "url" (I-default) noma "b64_json". |
image_url | Ukuhlobisa | Ngaphandle | Umbhalo ukuqala nge: a https:// umugqa we-maximum ye-4.096 ama-characters ngaphandle kwe-user name noma password, noma data:image/…;base64 I-URL (i-PNG, i-JPEG, i-WebP noma i-GIF; akukho i-SVG). I-Generator kuphela editImininingwane ze-Imunify requires_image_url. |
resolution is not used: ngamunye generator yenza ubukhulu yayo. Nge url, zonke izithombe zithunyelwe ku-Blossom ekhukhwini futhi unayo ikhonkco yayo (izinhlayiyana ezimbalwa zithunyelwe kuphela ikhonkco yayo yayo, okuyinto zithunyelwe). Wonke umuntu nge-link angakwazi ukufinyelela futhi akakwazi ukufinyelela; bheka Yintoni i-API angakwazi ukubonaNge
b64_json umbhalo ushiye ngesikhathi sokubambisana futhi akuyona engaphansi. A image sent as a data: Ukubuyekezwa image_url Ukubuyekezwa ngokufanayo njenge
ekhaya futhi ifakwe ku-Blossom okokuqala ukuze umkhakha ungathola; kususwa futhi uma isicelo akufanele ukufakelwa.
Uma ezinye n imiphumela imiphumela, ungakwazi ukufumana iziphumo ezisebenzayo, zihlanganisa kuphela iziphumo ezisebenzayo (ngezinye ama-providers zihlanganisa ngaphandle kokuphumelela), futhi nymbot.failed Ukubonisa inani elithile. Uma bonke abahlukile, isicelo ivumela 502.
Ukuphendula
{
"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 }
}
| Ukubuyekezwa | Kwangathi |
|---|---|
400 | Ngaphandle kwemvelo; n 1 kuya ku 4 (invalid_value); ubukhulu obuthandayo (invalid_size) noma isithombe (invalid_image, invalid_image_url); Model okuyinto kodwa akuyona umbhalo generator (invalid_model); isithombe ye-generator okuyinto awukwazi edit (edit_unsupported); akukho isithombe esithombe (image_required). |
402 | I-Balance ayikwazi ukuhlanganisa zonke izibonelelo ezivame. |
404 | (Hhayi isibonelo esithakazelisayo)model_not_found). |
502 | Ukuhlobisa (upstream_errorNgaphandle kokuba umphakeli umphakeli umphakeli umphakeli; ke umphakeli charged_sats. |
503 | Imibala ayikwazi ukuhanjiswa ngoku (media_hosting_unavailable). b64_json Ukusebenza futhi. |
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);
Ukubhalisa Images
Ukuguqulwa kwesithombe esithunyelwe, ngokuvamile. Lokhu kuyinto editing endpoint ye-OpenAI, ngakho-ke i-OpenAI SDKs' images.edit isebenza njengoko. Only Pro generators with edit ku-Model List ufumane.
POST https://nymbot.ai/api/v1/images/edits — unemibuzo ye-API, noma I-Lightning Payment ngesicelo• Umzimba multipart/form-dataNgaphezulu kwe-32 MB
| isikhunta | Uhlobo | Ukubalwa | Ukucaciswa |
|---|---|---|---|
image | Ngena ngemvume | Yebo | Umbhalo ukuguqulwa: PNG, JPEG, WebP noma GIF, kuze kube 20 MB. Kwakhona asatholakala image[]Okokuqala isetshenziswa. |
prompt | Ukuhlobisa | Yebo | Yini ukuguqulwa? |
model | Ukuhlobisa | Yebo | Generator nge edit. |
n | Ngena ngemvume | Ngaphandle | 1 ukuze 4. |
sizeaspect_ratioqualitynegative_promptoutput_format | Ukuhlobisa | Ngaphandle | Ukuze Generation. |
response_format | Ukuhlobisa | Ngaphandle | "b64_json" (I-default lapha) noma "url". |
Ukubhalisa umbhalo kuhlolwe ukuba i-PNG, JPEG, WebP noma GIF eyenziwe kahle, ifakwe njenge-type yayo yayo, futhi ifakwe ku-Blossom host, ngoba ama-generators zitholela ukufinyelela kwabo nge-link. Ukwelashwa njenge-public. Uma ukuguqulwa kwangapheli futhi akukho ukuguqulwa, i-copy ebhokisini iyahlaziywa. Ukuphendula inesibophelele njenge-generator. I-price yi-price ye-generators, okuyinto kunezinto zihlanganisa i-cost ye-input image.
Ukuphendula
{
"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 }
}
| Ukubuyekezwa | Kwangathi |
|---|---|
400 | Noma isithombe noma ifomu, ifayela okuyinto ayikho isithombe (invalid_image), noma generator okuyinto ayikwazi edit (edit_unsupported). |
413 | Ukubalwa kwevidiyo engaphezulu kwe-20 MB (file_too_large), noma isicelo ephelele engaphezu kuka-32 MB. |
503 | Umhlahlandlela (media_hosting_unavailable). |
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"));
Ividiyo
Ividiyo ivame imizuzu, ngakho-ke ivela emkhakheni. Ungathumela, ufike id ngokushesha, futhi ucebele id kuze kube. Yonke i-videogenerator ivame isilinganiso se-Pro.
POST https://nymbot.ai/api/v1/videos — unemibuzo ye-API, noma I-Lightning Payment ngesiceloImininingwane 202.
| isikhunta | Uhlobo | Ukubalwa | Ukucaciswa |
|---|---|---|---|
model | Ukuhlobisa | Yebo | I-Video Generator id kusuka ku- GET /api/v1/models?type=video, njenge veo. |
prompt | Ukuhlobisa | Yebo | Yini kufanele kube. |
duration | Inombolo noma string | Ngaphandle | Usetyenziswa kuphela generators ukuthi ungahambisa ubude; abanye ukwenza ubude yabo ngokuvamile, okuyinto seconds ku-response kanye ne-price elandelayo. |
aspect_ratio | Ukuhlobisa | Ngaphandle | Ukulungele "16:9" noma "9:16"; Usayizi efana "1280x720" Ukubuyekezwa kwe-Ratio. |
resolutionquality | Ukuhlobisa | Ngaphandle | Olandelayo: One of the Generator resolutions ku-model list, njenge "720p" noma "1080p". It is a price. Yonke okuzenzakalelayo is a refusal unsupported_resolution. |
image_url | Ukuhlobisa | Ngaphandle | Umbhalo ukuqala nge: a https:// Link noma A data:image/… I-URL, okuyinto ifakwe ku-host ye-Blossom ye-publish okokuqala. I-generator ye-Blossom requires_image_url. |
I-price iyatholakala lapho uthumele, ukusuka ku-generator, isizukulwane kanye ne-length, ngakho-ke kusetshenziswe ku-pro balance yakho uma umphakeli ukuthatha umsebenzi, futhi ifakwe njenge
cost, estimated_cost futhi nymbot. Uma umphakeli uxhumane umsebenzi, akugqoka. Uma umphakeli ngempumelelo ngemva, noma i-clip eyenziwe ayikwazi ukuvikelwa futhi umphakeli awukwazi ukufakelwa, umphakeli uxhumane nje, ngokuzenzakalelayo. Umphakeli owaqhubeka ngemva kwenyanga uxhumane, futhi uxhumane, ngoba umphakeli uxhumane umphakeli uma uxhumane. Umphakeli uxhumane i-credits kodwa akukunciphisa inani lokushintshwa we-key.
Ukuphendula (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 Ukuqala like in_progress, noma completed Ukubuyekezwa kwevidiyo data Ngemuva kwalokho, umugqa wahlala ngokushesha.
Ukubuyekeza ku-video
GET https://nymbot.ai/api/v1/videos/{id} - unemibuzo owenziwe yi-nym enikezela. Umbhali owenziwe ngempumelelo inikeza.
Ukuphendula 202 Phakathi nevidiyo yenzelwe futhi 200 Ngemuva kokufinyelela noma kwangapheli. Qaphela ngalinye amaminithi angu-5 kuya ku-10. Ngemuva kokufinyelela ngalinye i-check i-provider yakhelwe ngexesha lokufinyelela; akufinyelela ngevidiyo. Isikhathi sokufinyelela isikhathi se-24 emva kokufinyelela.
GET /api/v1/videos inikeza i-key's last 50 jobs njenge
{"object": "list", "data": […]}.
Ukuphendula (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 Yini in_progress, completed noma failedI-A Failed Job Carries error ({"code": "generation_failed", "message": …}(Wagqibela ukuhlaziywa kwebhizinisi) cost 0 futhi nymbot Thumela
refunded_credits futhi refunded_satsIvidiyo ephelele iyatholakala ku-Blossom host, njenge-images eyenziwe.
| Ukubuyekezwa | Kwangathi |
|---|---|
400 | Ngaphandle kwe-0 kuya ku-60 (invalid_value); isixazululo se-generator ayidinga (unsupported_resolution); akukho isithombe ye-generator enesidingo (image_required); imodeli okuyinto ayikho i-video generator (invalid_model). |
402 | I-Pro Balance ayikwazi ukucubungula i-video. |
404 | Okunye generator (model_not_found), noma akukho umsebenzi ngesi-id yakho ye-nym, noma i-nym engaphezulu kwe-24 amahora (video_not_found). |
429 | I-Your nym already has 10 videos rendering (video_jobs_limit). Hlola kwabo futhi ubhale ngaphezulu uma umphumela omnye. |
502 | Umkhakha wahlanganyela umsebenzi. Akukho ingxubevange ngaphandle kokuba umphakeli wahlanganyelwa. |
503 | Ividiyo ayikwazi ukudluliselwa noma ukugcina ngoku (media_hosting_unavailable, service_unavailable). |
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);
Umbhalo we-Speech
Ukubuyekeza ingxubevange futhi ivumela ifayela le-audio ngokuvamile, akuyona ingxubevange. It is OpenAI's speech endpoint, ngakho-ke audio.speech.create ku-OpenAI SDKs ukusebenza.
POST https://nymbot.ai/api/v1/audio/speech — unemibuzo ye-API, noma I-Lightning Payment ngesicelo.
| isikhunta | Uhlobo | Ukubalwa | Ukucaciswa |
|---|---|---|---|
model | Ukuhlobisa | Ngaphandle | Umhlahlandlela Umhlahlandlela Uhlobo lwe-Audio Models. Default: I-voice ye-standard, @cf/myshell-ai/melotts. aura-2 I-Deepgram Aura 2 |
input | Ukuhlobisa | Yebo | Umbhalo ukubuyekeza: up to 800 imibala for the standard voice, 2,000 for Aura 2. |
voice | Ukuhlobisa | Ngaphandle | I-voice id kusuka Imininingwane ye-voices: Aura umbhali efana luna (Uma aura-2-luna-en), noma ingxowa MeloTTS (en, es, fr, zh). OpenAI ama-voice ama-names efana alloy zihlanganisa futhi ukunikela ukubuyekezwa kwe-model. |
language | Ukuhlobisa | Ngaphandle | I-code ye-language efana esNgaphandle kwe-voice, i-voice ithatha i-voice ye-language. I-voice eyenza i-language ye-language. 422 voice_language_mismatch, futhi ulimi ukuthi imodeli ayikho isisindo 422 unsupported_language. |
response_format | Ukuhlobisa | Ngaphandle | I-Standard Voice iyahambisana mp3 I-Aura 2 iyahamba mp3 (Ukuhlukaniswa okuqhubekayo) opus, aac, flac, wav noma pcm. |
speed | Inombolo | Ngaphandle | Ukubuyekezwa futhi ukuncintisana. |
I-voice ye-standard inikeza i-flat 3 credit ye-standard (30 sats) isicelo, njenge-app. I-Aura 2 i-Pro, i-priced by the characters you send. I-response body yi-audio, nge-matching
Content-TypeI-cost is in the X-Nymbot-Cost-Sats umbhali. Uma umbhali umbhali akufanele, akufanele akukho.
Ukuphendula
HTTP/1.1 200 OK
Content-Type: audio/mpeg
X-Nymbot-Cost-Sats: 4.2
X-Nymbot-Balance-Sats: 41055.6
(audio bytes)
| Ukubuyekezwa | Kwangathi |
|---|---|
400 | Okungenani inguqulo; inguqulo ngaphezulu kwe-model limit (input_too_long); ifomati a model ayikwazi ukukhiqiza (unsupported_response_format); isisindo esaziwa (invalid_voice); imodeli okuyinto ayikho umzila umzila (invalid_model). |
422 | I-voice ayixazulule isilinganiso esithathwe, noma isibonelo ayikho isilinganiso esithathwe. |
502 | Umhlahlandlela umhlahlandlela umhlahlandlela. Akukho umhlahlandlela. |
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()));
Imodeli ye-audio kanye nemisindo
Kukho 41 Aura 2 ababhali-English kanye nezilimi ezine zeMeloTTS.
GET https://nymbot.ai/api/v1/audio/models - Akukho isikhwama esidingo.
GET https://nymbot.ai/api/v1/audio/voices?language=en - Akukho isikhwama esidingo.
| isikhunta | Uhlobo | Ukubalwa | Ukucaciswa |
|---|---|---|---|
language | isikhunta (Query) | Ngaphandle | Imininingwane kuphela ngezilimi. |
model | isikhunta (Query) | Ngaphandle | I-voices kuphela ye-model yayo. |
Ukusabela (ukudluliselwa)
{
"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 }
]
}
I-Models List Imibuzo {"object": "list", "data": {"tts": […], "stt": […]}}. Wonke imodeli wokubhalisa inikeza isilinganiso, ixabiso, max_input_chars,
response_formats, languages futhi default_voiceI-transcription model inikeza i-aliases yayo, max_file_bytes, max_seconds, ama-format kanye ne-price per minute.
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);
Umbhalo ku-Text
Ukuguqulwa kwe-record ku-text nge-Whisper. Lesi yindawo yokuqala ye-Transcription ye-OpenAI, ngakho
audio.transcriptions.create Ukusebenza
POST https://nymbot.ai/api/v1/audio/transcriptions — unemibuzo ye-API, noma I-Lightning Payment ngesicelo• Umzimba multipart/form-data.
| isikhunta | Uhlobo | Ukubalwa | Ukucaciswa |
|---|---|---|---|
file | Ngena ngemvume | Yebo | Ukubhalisa, kusuka ku-256 ama-byte kuya ku-25 MB kuya ku-30 amaminithi: WAV, WebM, MP4 noma M4A, Ogg noma Opus, MP3 kanye nezinye ama-format Whisper read. |
model | Ukuhlobisa | Ngaphandle | Ukukhangisa whisper, okuyinto Whisper Large v3 Turbo. whisper-1, whisper-large-v3-turbo futhi @cf/openai/whisper-large-v3-turbo Khetha okuhle. |
language | Ukuhlobisa | Ngaphandle | I-language eyenziwe, njenge en. Ukuhlobisa uma ushiye. |
prompt | Ukuhlobisa | Ngaphandle | Imininingwane noma ukubuyekezwa, njenge-imeyili. Kuncike izici ezingu-1000 ziye zisetshenziselwa. |
response_format | Ukuhlobisa | Ngaphandle | json (Ukuhlukaniswa okuqhubekayo) text, srt, vtt noma verbose_json. |
Ukuze i-WAV, i-WebM, i-MP4 kanye ne-Ogg amafayela, ubude lithunyelwe kusuka ku-file ngaphambi kokusebenza okungenani, ngakho-ke ukubuyekezwa kwe-30 amaminithi kuqala kuqala (ngokusho kwe-3 amaminithi). Ubude we-WAV ifayela lithunyelwe ngesantya yayo, ama-channels kanye ne-sample size. Ubude kwezinye amafayela, njenge-MP3, ayikwazi ukubuyekezwa kuqala, ngakho-ke zithunyelwe ngama-bitrate engaphansi: ku-Nymbot ibheka, i-8 kbps, i-30 amaminithi yi-1.8 MB, futhi ifayela elikhulu kulokhu ifomu lithunyelwe ku-Nymbot 413
audio_too_long Previous Previous post: Ukulandela ukubhuka okwengeziwe njenge-WAV, i-WebM, i-MP4 noma i-Ogg. Uma i-Whisper ibhalisele ngaphezulu kwama-30 amaminithi, isicelo esithathwe
413 audio_too_long, futhi kusukela Whisper wahlala, amaminithi angu-30 kubhalwe.
You pay for the length of the audio, rounded up to the second: the longest of the length read from the file, the length Whisper reports, and the least the file size allows, at Whisper's per-minute price with the usual fee and margin, and at least 0.05 credit a request. It is paid from the standard balance when that can cover the hold, and from Pro otherwise; 402 inikeza ukuthi isilinganiso kuyadingeka. Kwi-app, ukudluliselwa kwebhizinisi ye-voice kungenziwa mahhala; ku-API iyatholakala njalo. Uma i-Whisper akufanele, akufakwa akukho.
Ukuphendula
{
"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 Ukuguqulwa kwe-Clear Text srt futhi vtt Back subtitles, futhi
verbose_json Ukongeza isilimi, ubude kanye nezinhlangano ze-time. Ukuze ama-JSON ezimbini, i-cost iyatholakala emaphaketheni.
| Ukubuyekezwa | Kwangathi |
|---|---|
400 | Okungenani ifayela, ifayela ngaphandle kwe-audio eyenziwe (invalid_audio), isithombe esidumile, noma isampula okuyinto ayikho isampula se-transcription (invalid_model). |
402 | Futhi isilinganiso ayikwazi ukucacisa. |
413 | Ifayela ungaphezulu kwe-25 MB (file_too_large) noma ukubuyekeza engaphezulu kwe-30 amaminithi, noma, ngaphansi kwe-format ebonakalayo engaphakathi, engaphezulu kwe-1.8 MB (audio_too_long). |
502 | I-Whisper ayikwazi ukucubungula i-audio. Akukho ukulayishwa. |
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);
Ukuguqulwa kwe-speech ku-English
POST https://nymbot.ai/api/v1/audio/translations — unemibuzo ye-API, noma I-Lightning Payment ngesicelo• Umzimba multipart/form-data.
I-transcription efanayo, ne-fields efanayo ngaphandle kwe-transcription language, ama-limits kanye ne-price, kodwa i-text iyatholakala e-English kungekho isilimi esebenzayo. I-OpenAI SDK ibizwa 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);
Ukuhlobisa
Ukuguqulwa kwe-text ku-vectors yokufunda, ukuxhumana kanye nokuguqulwa kwe-deduplication. Amamodeli asebenza ku-Cloudflare futhi zithole isilinganiso se-standard.
POST https://nymbot.ai/api/v1/embeddings — unemibuzo ye-API, noma I-Lightning Payment ngesicelo.
| isikhunta | Uhlobo | Ukubalwa | Ukucaciswa |
|---|---|---|---|
model | Ukuhlobisa | Yebo | I-embedded model kusuka GET /api/v1/models?type=embedding. |
input | String noma Array of Strings | Yebo | Umbhalo wokubacindezela, okungenani ama-strings angu-100 ngaphandle kokuzihlanganisa. Izithombe ze-token zihlanganiswa (token_input_unsupported(Wonke inguqulo kufanele ifakwe imodeli context_length, zihlanganisa njengama-byte angu-4 i-token. |
encoding_format | Ukuhlobisa | Ngaphandle | float (I-default) noma base64 (I-Little-endian 32-bit ye-floats) |
dimensions | Ngena ngemvume | Ngaphandle | Umbala we-model, noma umbala we-model supported_dimensions One of those; Vector is then shortened and normalized. Yonke okuzenzakalelayo iyahlekile. |
| Umhlahlandlela | Ukuphakama | Ngena ngemvume |
|---|---|---|
@cf/baai/bge-m3 | 1024 izilimi eziningi | 8,192 izitolo |
@cf/qwen/qwen3-embedding-0.6b | 1024 izilimi eziningi | 8,192 izitolo |
@cf/baai/bge-large-en-v1.5 | 1024, IsiZulu | 512 izikhwama |
@cf/baai/bge-base-en-v1.5 | 768, IsiZulu | 512 izikhwama |
@cf/baai/bge-small-en-v1.5 | 384, IsiZulu | 512 izikhwama |
Umhlahlandlela wama-models iyisisombululo owaziwa ukuthi kukhona futhi ukuthi kunezimali; I-Google's EmbeddingGemma, nge-vectors ezincinane ku-request, ibonisa khona futhi uma ikhathanisi ine-price yayo. Izinhlangano zihlanganiswa ngalinye-token yokufinyelela, futhi i-0.05-credit minimum isetshenziselwa ngamunye isicelo, akuyona ngamunye isicelo, ngakho-ke ukwahlukanisa imithombo eminingi ku-request eyodwa kunezinto engcono kunezinye.
Ukuphendula
{
"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 }
}
| Ukubuyekezwa | Kwangathi |
|---|---|
400 | Ngaphandle kwe-Input noma i-Empty One; i-token array (token_input_unsupported); ezingaphezu kuka-100 ingxube (too_many_inputs); inguqulo eside kunazo imodeli (input_too_long); ubungakanani ungathumela model (unsupported_dimensions). |
402 | Isilinganiso se-standard iyatholakala kakhulu. Ama-embeddings akufanele usebenzisa isilinganiso se-Pro. |
404 | Ngaphandle kokuzihlanganisa umugqa nge-imeyili. |
502 | Model ifakwe. Akukho ifakwe. |
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);