Peke ki ngā ihirangi

VibeVoice 1.5B

Whakauru

id tauira vibevoice
# 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/vibevoice?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "speakers": [
      {
        "preset": "Frank [EN]"
      },
      {
        "preset": "Carter [EN]"
      }
    ]
  }'

# 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"

Tēnei tono: ≈$ 0.02 20 whiwhinga API Whakahaerehia ki tēnei whārangi

Tikina he kī API
Microsoft Kuputuhi ki te Kōrero #text-to-speech#multi-speaker#podcast

He kuputuhi-ki-te-kōrero mō ngā kaikōrero maha, mō ngā tuhinga roa pēnei i ngā podcast, me ngā reo mō ia kaikōrero

Microsoft · Ororongo

Kei konei tō hua tuatahi

Hangaia he tono ki raro nei, ka whakahaere mā tō kī API. Ka tāruatia ngā putanga ki tō mātou rokiroki, ka puritia mō ake tonu atu, mō rānei 7 rā mō te kore utu.

Hangaia he tono

Ka hangaia ngā mana whakahaere mai i te aronuinga o te tauira. Ka whakahoungia te waehere me te utu ina whakarerekē koe.

•e hiahiatia ana 88 / 90000

Tuhinga tāuru kōrero, me ngā tapanga kōwhiringa 'Speaker X:' hei wehe i ngā kaikōrero i te kōrerorero.

•e hiahiatia ana

Ka whakatauhia aunoatia ngā kaikōrero mā te tuhinga, mā ngā tauira reo rānei; tukuna he rārangi hei tohu āta i a rātou.

Arā atu cfg_scale · seed · enable_safety_checker
taunoa 1.3

Mā te kaha CFG (Classifier-Free Guidance) e whakatau te piri o te whakaputanga ki te kuputuhi; ka kaha ake te whai ina piki te tautuhinga.

Kākano matapōkere e taea ai te whakahoki anō i te whakaputanga.

POST /run/vibevoice?wait=20 utu → $ 0.02
# 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/vibevoice?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "speakers": [
      {
        "preset": "Frank [EN]"
      },
      {
        "preset": "Carter [EN]"
      }
    ]
  }'

# 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"

Whakahaerehia tēnei tono

Ka noho tō kī ki tēnei pūtirotiro: ka tukuna ki te Doitong API anake, ā, ka tiakina ki te localStorage anake ina tohua e koe te Mahara. Tikina he kī API

Mō VibeVoice 1.5B

Ka huri i tētahi `script` tae atu ki te 90000 pūāhua hei kōrero. Ka taea e te kōrero te whakamahi i ngā tīmatanga 'Speaker X:', ā, mā te rārangi `speakers` e hiahiatia ana e tautuhi ngā reo. Ko te awhe `cfg_scale` 1 ki te 2, ā, ka whakahaere i te piri ki te kuputuhi; mā `seed` e taea ai te tukurua o ngā oma. Ka whakahoki oro me te roanga me te sample rate.

Ngā tawhā

IngoaMomo TaunoaE whakaaetia ana Whakamārama
scripte hiahiatia ana
Momostring
≤ 90,000 pūāhua
Tuhinga tāuru kōrero, me ngā tapanga kōwhiringa 'Speaker X:' hei wehe i ngā kaikōrero i te kōrerorero.
speakerse hiahiatia ana
Momoobject[]
Ka whakatauhia aunoatia ngā kaikōrero mā te tuhinga, mā ngā tauira reo rānei; tukuna he rārangi hei tohu āta i a rātou.
speakers[].presetkōwhiringa
Momoenum
TaunoaAlice [EN]
Alice [EN]Carter [EN]Frank [EN]Mary [EN] (Background Music)Maya [EN]Anchen [ZH] (Background Music)Bowen [ZH]Xinran [ZH]
Tatūkē reo whakakapi mō te kaikōrero kāore he `audio_url`; ka noho matua te tauira ororongo kua tukuna ki runga ake i te tatūkē.
speakers[].audio_urlkōwhiringa
Momourl · audio
URL kōnae ororongo tauira reo; mā te tuku ka whakakapi i `preset`.
seedkōwhiringa
Momointeger | null
Kākano matapōkere e taea ai te whakahoki anō i te whakaputanga.
cfg_scalekōwhiringa
Momonumber
Taunoa1.3
1 – 2
Mā te kaha CFG (Classifier-Free Guidance) e whakatau te piri o te whakaputanga ki te kuputuhi; ka kaha ake te whai ina piki te tautuhinga.
enable_safety_checkerkōwhiringa
Momoboolean
Taunoatrue
Ka taea te whakangāwari i te tātari mā te tautuhi false, mēnā he mana tō te kaiwhakatuwhera.
e hiahiatia ana

Putanga

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "vibevoice",
  "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": 20,
    "usd": "0.02",
    "charged": 20,
    "refunded": 0
  },
  "input": {
    "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "speakers": [
      {
        "preset": "Frank [EN]"
      },
      {
        "preset": "Carter [EN]"
      }
    ]
  },
  "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
    },
    "duration": 5,
    "sample_rate": 24000,
    "generation_time": 5.6,
    "rtf": 0.53
  },
  "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"
  }
}
Ō kōnae, māu e whiriwhiriKo ia url o outputs[] he tārua kei tō mātou rokiroki: ka puritia mō ake tonu atu (ka utua ia GB-marama) mō rānei 7 rā mō te kore utu, e ai ki ngā tautuhinga o tō pūkete, ki te ?storage= rānei.
He ōrite te hanga ki ia tauiratype, url, content_type, width, height me duration, mō ngā pikitia, ataata me te oro. Ko output te ahanoa hua ake o te tauira.
Ngā āpure o te putanga
audio
object {url, content_type, file_name, file_size}Kōnae ororongo kei roto te kōrero kua waihangatia.
duration
numberTe roa o te putanga ororongo, ka inehia ki te hēkona.
sample_rate
integerAuau tauira o te putanga ororongo.
generation_time
numberTe wā whakaputa ororongo, ka inehia ki te hēkona.
rtf
numberTauwehe wā-tūturu ka tātaihia hei generation_time kua whakawehea ki te audio_duration; ko ngā uara iti ake he pai ake te mahi.

Ētahi atu tauira: Kuputuhi ki te Kōrero

Mō ngā āpiha AI: kei te wātea tēnei whārangi hei Markdown ki https://doitong.com/mi/developers/models/vibevoice.md. Ngā tauira me ngā aratohu katoa: https://doitong.com/developers/llms.txt