Dža ko lil

Stable Audio 3 Medium Base Audio to Audio

Integriruj

Modelosko id stable-audio-3/medium/base/audio-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/stable-audio-3/medium/base/audio-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",
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# 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"

Kava mangipen: $0.053 53 API krediti · ≈ ₽5.70 Phir les kate

Lel API klidin
Stability AI Audio 1–380 s #music#style-transfer#remix

Base-checkpoint Medium audio-to-audio remix: parivarel jekh źutno klipo promptesa, dži 380 sekundǎ

Stability AI · Audio

Tiro prvo rezultato si kate

Ker tele jekh mangipen thaj phir les tire API klidinosa. E rezultatur si kopirime amare arakhipneste, vično vaj 7 dives bilačhes.

Ker jekh mangipen

O kontrolura kerde si katar e schemaske. O kodo thaj e cena menjinen sar tu len menjines.

•trubul

Tekstoske instrukcije save deskribinen e transformacija savo si te kerel pes ko source-audio.

•trubul audio_url
Čhiv jekh fajl, vaj

Inputosko audio vaš transformacija.

standardno 30

Audiosko lungipen ande sekunda, medium-modelosko maksimum 380 sekunda (aproksimativno 6 minuta 20 sekunda).

Lučhe negative_prompt · output_format · bitrate · num_inference_steps · guidance_scale · init_noise_level · seed · enable_prompt_expansion · enable_safety_checker
standardno

Teksto savo sikavel na-kamle kvaliteta ando rezultato.

output_format standardno mp3

Containerosko formato uživardo vaš o rezultatosko audio.

standardno 192k

Rezultatosko audiosko bitrate, ignoririme kana uživarel pes wav vaj flac vašoda si lossless. Vaš compressed format sar mp3, aac, vaj opus, den jekh vredno ande forma '192k' vaj '320k'.

standardno 50

Alosar keti samplingoske stepa te keren, približno 50 te den lačhi kvaliteta kana uživaren base (non-distilled) checkpointa.

standardno 7

Classifier-free guidanceoski zor; približno 7.0 si rekomendime sar angluno vredno ko base checkpointa; te vazdes les kerel o keripe maj paše pasavipasko e promptosa.

standardno 0.9

Source-audiosko šumosk o nivelo: 0.1 arakhel paše sajekhipen e inputosa, 0.5 si maškarutno thaj 1.0 paruvavel savoro source šumesa vaš čisto keripe.

Randomno generatorosko seed vaš ponovljivo rezultata; te mukhes les avri, si len randomno seed.

POST /run/stable-audio-3/medium/base/audio-to-audio?wait=20 hesab → $0.053
# 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/stable-audio-3/medium/base/audio-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",
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# 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"

Phandel kava mangipen

Tiro kluč ačhel kadale browsereste: bičhalel pes numa ko Doitong API thaj šuvav pes (localStorage) numa te tiknes Remember. Le jekh API ključ

Palal Stable Audio 3 Medium Base Audio to Audio

Lel jek source klipo katar `audio_url` thaj teksto `prompt`, thaj kerel jek transformime varianta. `init_noise_level` (0 dži 1) phenel sar but o rezultato palal o inputo džal, a `duration` lel 1 dži 380 sekunda. Kada si non-distilled checkpoint, standardura si 50 sampling paso thaj lidžaripe scale 7. O rezultato šaj te ovel mp3, wav, flac, ogg, opus, m4a vaj aac.

Parametra

Bičhalav vaj e kanonikano nav vaj e native nav, na duj. Kanonikane nava

NavTip standardnoMuklo Vakeripe
negative_promptopcionalno
Tipstring
standardno
Teksto savo sikavel na-kamle kvaliteta ando rezultato.
durationopcionalno
Tipnumber
standardno30
1 – 380
Audiosko lungipen ande sekunda, medium-modelosko maksimum 380 sekunda (aproksimativno 6 minuta 20 sekunda).
num_inference_stepsopcionalno
Tipinteger
standardno50
1 – 100
Alosar keti samplingoske stepa te keren, približno 50 te den lačhi kvaliteta kana uživaren base (non-distilled) checkpointa.
guidance_scaleopcionalno
Tipnumber
standardno7
0 – 25
Classifier-free guidanceoski zor; približno 7.0 si rekomendime sar angluno vredno ko base checkpointa; te vazdes les kerel o keripe maj paše pasavipasko e promptosa.
seedopcionalno
Tipinteger | null
Randomno generatorosko seed vaš ponovljivo rezultata; te mukhes les avri, si len randomno seed.
enable_prompt_expansionopcionalno
Tipboolean
standardnofalse
Promptosko bararipen LLM-esa kana si phandlo, savo del detalura thaj federel e rezultatoski kvaliteta.
enable_safety_checkeropcionalno
Tipboolean
standardnotrue
Sigurnosko kontrolirimos vaš NSFW kontento.
output_formatopcionalno
Tipenum
standardnomp3
mp3wavflacoggopusm4aaac
Containerosko formato uživardo vaš o rezultatosko audio.
bitrateopcionalno
Tipstring
standardno192k
Rezultatosko audiosko bitrate, ignoririme kana uživarel pes wav vaj flac vašoda si lossless. Vaš compressed format sar mp3, aac, vaj opus, den jekh vredno ande forma '192k' vaj '320k'.
prompttrubul
Tipstring
Tekstoske instrukcije save deskribinen e transformacija savo si te kerel pes ko source-audio.
audio_urltrubul audio
Tipurl · audio
Inputosko audio vaš transformacija.
init_noise_levelopcionalno
Tipnumber
standardno0.9
0 – 1
Source-audiosko šumosk o nivelo: 0.1 arakhel paše sajekhipen e inputosa, 0.5 si maškarutno thaj 1.0 paruvavel savoro source šumesa vaš čisto keripe.
trubul Kanonikano nav, vi akceptime

Fajloske parametra lel jekh publikano https:// URL, jekh data: URI dži 10 MB, vaj e file_url uploadoski. Fajlura

Rezultato

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "stable-audio-3/medium/base/audio-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": 53,
    "usd": "0.053",
    "charged": 53,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "output": {
    "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
    },
    "seed": 42,
    "prompt": "string"
  },
  "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"
  }
}
Tire fajlura, tiro alosaripenSako outputs[].url si kopija amare arakhipneste: vično (čargeime per GB-mase) vaj 7 dives bilačhes, tiro kontoskere regulaciatar vaj ?storage=.
Sa jekh forma sako modeloθartype, url, content_type, width, height thaj duration, varesave imajinake, video thaj audio-ke. output si o modelosko korkoro resultosko objekto.
Outputoske fieldura
audio
object {url, content_type, file_name, file_size}Audio-klipo kerdino katar keripe.
seed
integerSeed savo kontrolisardas randomizacia ande keripe.
prompt
stringPromptos savo si upotreblime vaš rezultatoski keripe.

Bute modeli: Audio

AI agentenge: kadija rig sar Markdown si kate https://doitong.com/rom/developers/models/stable-audio-3/medium/base/audio-to-audio.md. Sa e modelura thaj e gidura: https://doitong.com/developers/llms.txt