Ruka hadi kwenye maudhui

VEED Clean Audio

Unganisha

Kitambulisho cha modeli veed/clean-audio
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/veed/clean-audio?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "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.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Faili kama mfano: $ 0.013 salio za API 13 faili zako hupimwa kabla ya kuendesha Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
VEED Sauti #speech-enhancement#noise-reduction#audio-denoise

Huondoa kelele kwenye sauti ya mazungumzo, husafisha rekodi zenye kelele au wimbo wa sauti wa video na kusawazisha urefu wa sauti

VEED · 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

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

•inahitajika audio_url
Dondosha faili, au

Rekodi inayotolewa kwa usafishaji kupitia URL ya umma au URI ya data, ikikubali sauti au video yoyote inayoweza kusimbuliwa na ffmpeg, ikijumuisha wav, ogg, mp3, webm, m4a, mov, aac, na mp4. Kwa video, uchakataji hutumia njia ya sauti; ita /video ili kupokea video yenye sauti iliyosafishwa, na rekodi za njia nyingi huchanganywa kuwa mono. Muda wa juu ni dakika 30, na kikomo cha ukubwa ni 512 MB.

Ya kina output_format · strength · target_lufs
output_format chaguomsingi flac

Chaguo la kontena la sauti: FLAC huhifadhi ubora usio na hasara kwa takriban nusu ya ukubwa wa faili la WAV. Tokeo lina njia moja katika 48 kHz yenye sampuli za biti 16.

chaguomsingi 0.874

Nguvu ya kupunguza sauti ya mandharinyuma ya usemi: mipangilio ya chini huhifadhi sauti zaidi ya chumba chini ya sauti, lakini mapumziko kati ya maneno husafishwa kabisa bila kujali. Kiwango cha chini cha sauti ya awali iliyosalia ni 1 minus strength; chaguomsingi ya 0.874 inalingana na mpangilio uliothibitishwa wa -18 dB.

chaguomsingi -19

Lengo la loudness ya tokeo iliyounganishwa chini ya ITU-R BS.1770; kutoa null kupitia API hupita urekebishaji na kuhifadhi kiwango cha chanzo. Vinginevyo, chaguomsingi ni -19 LUFS, likilingana na tokeo la kihariri cha VEED, na kilele halisi ni -1.1 dBTP.

POST /run/veed/clean-audio?wait=20 makadirio → $ 0.013
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/veed/clean-audio?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "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.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Endesha ombi hili

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

Kuhusu VEED Clean Audio

Huondoa kelele za mandharinyuma kutoka rekodi za mazungumzo. `audio_url` hukubali umbizo lolote la sauti au video ambalo ffmpeg inaweza kusoma. `strength` (0-1) huweka kiwango cha uondoaji wakati wa mazungumzo, na `target_lufs` (-40 hadi -8) huweka urefu wa sauti ya matokeo, au inaweza kuachwa. Matokeo ni mono ya 48 kHz, 16-bit, kama flac au wav, yenye muda sawa na ingizo.

Vigezo

Tuma jina rasmi au jina asilia, si yote mawili. Majina rasmi

JinaAina ChaguomsingiInaruhusiwa Maelezo
audio_urlinahitajika audio
Ainaurl · audio
Rekodi inayotolewa kwa usafishaji kupitia URL ya umma au URI ya data, ikikubali sauti au video yoyote inayoweza kusimbuliwa na ffmpeg, ikijumuisha wav, ogg, mp3, webm, m4a, mov, aac, na mp4. Kwa video, uchakataji hutumia njia ya sauti; ita /video ili kupokea video yenye sauti iliyosafishwa, na rekodi za njia nyingi huchanganywa kuwa mono. Muda wa juu ni dakika 30, na kikomo cha ukubwa ni 512 MB.
strengthsi lazima
Ainanumber
Chaguomsingi0.874
0 – 1
Nguvu ya kupunguza sauti ya mandharinyuma ya usemi: mipangilio ya chini huhifadhi sauti zaidi ya chumba chini ya sauti, lakini mapumziko kati ya maneno husafishwa kabisa bila kujali. Kiwango cha chini cha sauti ya awali iliyosalia ni 1 minus strength; chaguomsingi ya 0.874 inalingana na mpangilio uliothibitishwa wa -18 dB.
target_lufssi lazima
Ainanumber | null
Chaguomsingi-19
-40 – -8
Lengo la loudness ya tokeo iliyounganishwa chini ya ITU-R BS.1770; kutoa null kupitia API hupita urekebishaji na kuhifadhi kiwango cha chanzo. Vinginevyo, chaguomsingi ni -19 LUFS, likilingana na tokeo la kihariri cha VEED, na kilele halisi ni -1.1 dBTP.
output_formatsi lazima
Ainaenum
Chaguomsingiflac
flacwav
Chaguo la kontena la sauti: FLAC huhifadhi ubora usio na hasara kwa takriban nusu ya ukubwa wa faili la WAV. Tokeo lina njia moja katika 48 kHz yenye sampuli za biti 16.
inahitajika Jina rasmi, pia linakubalika

Vigezo vya faili vinakubali URL ya umma ya https://, data: URI ya hadi 10 MB, au file_url ya upakiaji. Faili

Tokeo

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "veed/clean-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": 13,
    "usd": "0.013",
    "charged": 13,
    "refunded": 0
  },
  "input": {
    "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
    },
    "audio_duration": 1.0
  },
  "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.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/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
audio
object {url, content_type, file_name, file_size}Sauti iliyosafishwa yenye muda unaolingana na chanzo, ikiwa na urekebishaji wa loudness. Rekodi ina njia moja, kiwango cha sampuli cha 48 kHz, na kina cha biti 16.
audio_duration
numberMuda wa ingizo, unaopimwa kwa sekunde.

Miundo zaidi: Sauti

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/veed/clean-audio.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt