Mirelo SFX2.0 · Text to Audio

Unganisha

Kitambulisho cha modeli mirelo-ai/sfx2.0/text-to-audio

# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/mirelo-ai/sfx2.0/text-to-audio?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const API = "https://api.doitong.ru/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/mirelo-ai/sfx2.0/text-to-audio?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");

import os
import requests

API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/mirelo-ai/sfx2.0/text-to-audio", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])

# 1. Connect once (Claude Code; Cursor, VS Code, Claude Desktop: https://doitong.com/sw/developers/docs/mcp)
claude mcp add --transport http doitong-models https://api.doitong.ru/v1/mcp \
  --header "Authorization: Bearer $DOITONG_API_KEY"

# 2. Your agent calls the "run" tool with:
{
  "model_id": "mirelo-ai/sfx2.0/text-to-audio",
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }
}

Piga modeli ya Mirelo SFX2.0 · Text to Audio (mirelo-ai/sfx2.0/text-to-audio) kupitia Doitong API. Nyaraka za mawakala: https://doitong.com/sw/developers/models/mirelo-ai/sfx2.0/text-to-audio.md

POST https://api.doitong.ru/v1/run/mirelo-ai/sfx2.0/text-to-audio?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json

{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}

Ikiwa hali ya jibu ni "queued" au "running", piga GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 mara kwa mara hadi iwe "succeeded"; faili ziko kwenye outputs[].url. POST https://api.doitong.ru/v1/quote/mirelo-ai/sfx2.0/text-to-audio yenye mwili uleule hurejesha bei kamili kabla ya kuendesha.

Faili kama mfano: $ 0.60 salio za API 600 · ≈ ₽ 64.39 faili zako hupimwa kabla ya kuendesha Iendeshe kwenye ukurasa huu

Pata ufunguo wa API

Mirelo AI Sauti 0.1–600 s #text-to-audio#sfx

Athari za sauti kutokana na maelezo ya maandishi, zikiwa na kidokezo hasi, muda na sampuli kadhaa

OpenAPI Markdown

Mirelo AI · Sauti

Tokeo lako la kwanza linaonekana hapa

Unda ombi hapa chini na uliendeshe kwa ufunguo wako wa API. Matokeo yanakiliwa kwenye hifadhi yetu, yakihifadhiwa milele au 7 siku bila malipo.

Unda ombi

Bei kwa kila sekunde ya sauti yako ya kutolewa

Bei kulingana na uingizaji wako

$ 0.01 / sekunde ya sauti ya tokeo

salio za API 10 / sekunde ya sauti ya tokeo · ≈ ₽ 1.07

Ombi hili: sekunde 60 × $ 0.01 $ 0.60 salio za API 600 · ≈ ₽ 64.39

Endesha · $ 0.60

Hutozwa tu ikifanikiwa, na kurejeshewa kiotomatiki ikishindwa.

duration chaguomsingi 30

num_samples chaguomsingi 2

Faili zako hupimwa kabla ya kuendeshwa (urefu, mwonekano, kasi ya fremu); makadirio hurejesha bei kamili na uendeshaji hutozwa kiasi hicho hicho.

Endpoint ya makadirio: POST /quote/{id}

Unda ombi

Vidhibiti vinazalishwa kutoka kwenye schema ya modeli. Msimbo na bei husasishwa unapovibadilisha.

prompt •inahitajika 88 / 2000

Maelezo ya athari ya sauti inayotakiwa.

duration chaguomsingi 30

Urefu wa sauti ulioombwa, unaopimwa kwa sekunde, lazima ulingane na kiwango cha juu maalum cha deployment cha text-to-SFX.

num_samples chaguomsingi 2

Idadi ya sampuli za uzalishaji ndani ya upitishaji mmoja wa mbele uliounganishwa.

Ya kina negative_prompt · upload_audio_format · upload_audio_bitrate_kbps · seed

negative_prompt 0 / 1000

Sauti za kuondoa kwenye tokeo.

upload_audio_format chaguomsingi wav

Umbizo linalotumika kwa kila faili ya sauti.

upload_audio_bitrate_kbps

Ubadilishaji wa bitrate ya upakiaji kwa kbps, unaokataliwa wakati upload_audio_format ni lossless; kuiacha bila kuwekwa huhifadhi LAME V0 VBR kwa mp3 au lengo la 256 kbps kwa aac. Kwa mp3, chagua kasi thabiti kamili kutoka 32, 40, 48, 56, 64, 80, 96, 112, 128, 160, 192, 224, 256, 320. Kwa aac, thamani kutoka 32 hadi 256 hubainisha lengo la encoder badala ya kasi iliyohakikishwa, hivyo sauti ya mono au iliyo na data chache inaweza kuwa chini yake.

seed

Seed ya sampuli ya kwanza; seed nasibu hutumiwa kwa -1 au inapokosekana.

POST /run/mirelo-ai/sfx2.0/text-to-audio?wait=20 makadirio → $ 0.60

# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/mirelo-ai/sfx2.0/text-to-audio?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const API = "https://api.doitong.ru/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/mirelo-ai/sfx2.0/text-to-audio?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");

import os
import requests

API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/mirelo-ai/sfx2.0/text-to-audio", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "mirelo-ai/sfx2.0/text-to-audio",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "wait_seconds": 20
    }
  }
}

Endesha ombi hili

Ufunguo wa API

Key yako inabaki kwenye kivinjari hiki: inatumwa kwa Doitong API pekee na kuhifadhiwa (localStorage) tu ukiweka tiki kwenye Kumbuka. Kumbuka katika kivinjari hiki Pata ufunguo wa API

Kuhusu Mirelo SFX2.0 · Text to Audio

Huzalisha athari za sauti kutoka kwa `prompt` yenye hadi herufi 2000, huku `negative_prompt` ikiondoa sauti zisizohitajika. `duration` huanzia sekunde 0.1 hadi 600 (chaguomsingi 30), na `num_samples` huzalisha matoleo 1 hadi 4, kila moja ikiwa na mbegu yake. Fomati ya tokeo ni wav, mp3, aac au flac kupitia `upload_audio_format`, ikiwa na bitrate ya hiari kwa mp3 na aac.

Vigezo

JinaAina ChaguomsingiInaruhusiwa Maelezo

promptinahitajika

Ainastring

≤ herufi 2,000

Maelezo ya athari ya sauti inayotakiwa.

negative_promptsi lazima

Ainastring | null

≤ herufi 1,000

Sauti za kuondoa kwenye tokeo.

durationsi lazima

Ainanumber

Chaguomsingi30

0.1 – 600

Urefu wa sauti ulioombwa, unaopimwa kwa sekunde, lazima ulingane na kiwango cha juu maalum cha deployment cha text-to-SFX.

seedsi lazima

Ainainteger | null

-1 – 9,223,372,036,854,776,000

Seed ya sampuli ya kwanza; seed nasibu hutumiwa kwa -1 au inapokosekana.

num_samplessi lazima

Ainainteger

Chaguomsingi2

1 – 4

Idadi ya sampuli za uzalishaji ndani ya upitishaji mmoja wa mbele uliounganishwa.

upload_audio_formatsi lazima

Ainaenum

Chaguomsingiwav

wavmp3aacflac

Umbizo linalotumika kwa kila faili ya sauti.

upload_audio_bitrate_kbpssi lazima

Ainainteger | null

32 – 320

inahitajika

Tokeo

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t

{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "mirelo-ai/sfx2.0/text-to-audio",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 600,
    "usd": "0.60",
    "charged": 600,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "model": "sfx-2.0",
    "audio": [
      {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
        "content_type": "audio/mpeg",
        "file_name": "0-output.mp3",
        "file_size": 1843200
      }
    ],
    "seeds": [
      42
    ]
  },
  "outputs": [
    {
      "type": "audio",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_size": 1843200,
      "duration": 12,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}

Faili zako, chaguo lakoKila outputs[].url ni nakala kwenye hifadhi yetu: huhifadhiwa milele (hutozwa kwa GB kwa mwezi) au 7 siku bila malipo, kulingana na mpangilio wa akaunti yako au ?storage=.

Muundo uleule kwenye kila modelitype, url, content_type, width, height na duration, kwa picha, video na sauti. output ni kitu cha matokeo cha modeli yenyewe.

Sehemu za tokeo

model: stringToleo la modeli ya SFX lililotumika kutengeneza tokeo.
audio: array of object {url, content_type, file_name, file_size}Athari za sauti zilizozalishwa, zikiwa na tokeo moja kwa kila sampuli.
seeds: array of integerSeeds zinazolingana na sampuli, zikihifadhi mpangilio wake.

Miundo zaidi: Sauti

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/mirelo-ai/sfx2.0/text-to-audio.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt

Tokeo lako la kwanza linaonekana hapa

Unda ombi

Endesha ombi hili

Kuhusu Mirelo SFX2.0 · Text to Audio

Vigezo

Tokeo

Tofauti nyingine za Mirelo SFX2.0

Mirelo SFX2.0 · Video to Video Tofauti: 3

Mirelo SFX2.0 · Video to Audio Tofauti: 3

Miundo zaidi: Sauti

MMAudio V2 Tofauti: 2

DeepFilterNet 3

Demucs

ElevenLabs Audio Isolation Tofauti: 4