Tada

Unganisha

Kitambulisho cha modeli tada/3b/text-to-speech

# 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/tada/3b/text-to-speech?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",
    "prompt": "Hello from Doitong. This is a short test sentence."
  }'

# 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"

const API = "https://api.doitong.com/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/tada/3b/text-to-speech?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "prompt": "Hello from Doitong. This is a short test sentence."
  }),
});
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.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "prompt": "Hello from Doitong. This is a short test sentence.",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/tada/3b/text-to-speech", 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.com/v1/mcp \
  --header "Authorization: Bearer $DOITONG_API_KEY"

# 2. Your agent calls the "run" tool with:
{
  "model_id": "tada/3b/text-to-speech",
  "input": {
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "prompt": "Hello from Doitong. This is a short test sentence."
  }
}

Piga modeli ya Tada (tada/3b/text-to-speech) kupitia Doitong API. Nyaraka za mawakala: https://doitong.com/sw/developers/models/tada/3b/text-to-speech.md

POST https://api.doitong.com/v1/run/tada/3b/text-to-speech?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json

{
  "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
  "prompt": "Hello from Doitong. This is a short test sentence."
}

Ikiwa hali ya jibu ni "queued" au "running", piga GET https://api.doitong.com/v1/requests/REQUEST_ID?wait=20 mara kwa mara hadi iwe "succeeded"; faili ziko kwenye outputs[].url. POST https://api.doitong.com/v1/quote/tada/3b/text-to-speech yenye mwili uleule hurejesha bei kamili kabla ya kuendesha.

Ombi hili: $ 0.004 salio za API 4 Iendeshe kwenye ukurasa huu

Pata ufunguo wa API

Open model Maandishi hadi Matamshi

Maandishi-hadi-hotuba yenye kunakili sauti, inayotamka maandishi yako kwa sauti ya klipu ya marejeleo, ikiwa na misimbo 10 ya lugha

OpenAPI Markdown

Open model · 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.

prompt •inahitajika

Maudhui ya usemi yaliyotolewa kama maandishi; mzungumzaji wa marejeo hutoa sauti inayotumika kuyatoa.

audio •inahitajika audio_url

Dondosha faili, au

Chanzo cha kunakili sauti kilichotolewa kama URL ya faili ya sauti, kinachomtambulisha mzungumzaji ambaye sifa zake za sauti zinapaswa kuigwa na modeli.

Ya kina output_format · transcript · language · num_extra_steps · temperature · top_p · repetition_penalty · acoustic_cfg_scale · noise_temperature · num_inference_steps · speed_up_factor · enable_safety_checker

output_format chaguomsingi wav

Muundo wa faili wa sauti iliyozalishwa.

transcript chaguomsingi

Unukuzi wa sauti ya marejeo ambao lazima utolewe kwa rekodi za lugha nyingine isipokuwa Kiingereza; unukuzi wa kiotomatiki umejengwa kwa Kiingereza pekee.

language chaguomsingi en

Msimbo wa lugha wa upangaji wa maandishi, ambao lazima ulingane na lugha ya usanisi unapozalisha usemi katika lugha nyingine isipokuwa Kiingereza.

num_extra_steps chaguomsingi 0

Idadi ya hatua za ziada za autoregressive za kuongeza prosody au ukimya wa mwisho kwa kuendeleza usemi zaidi ya maandishi yaliyotolewa.

temperature chaguomsingi 0.6

Halijoto ya sampuli ya tokeni za maandishi: kuiongeza huongeza utofauti wa tokeo, na 0 au chini hairuhusiwi.

top_p chaguomsingi 0.9

Mpangilio wa sampuli wa Top-p (nucleus) unaotumika kuzalisha maandishi.

repetition_penalty chaguomsingi 1.1

Adhabu ya kurudiwa kwa tokeni wakati wa kuzalisha tokeo.

acoustic_cfg_scale chaguomsingi 1.6

Nguvu ya mwongozo usio na classifier inayotumika kuzalisha vipengele vya akustika.

noise_temperature chaguomsingi 0.9

Halijoto ya kelele inayotumika wakati wa diffusion ya flow-matching.

num_inference_steps chaguomsingi 20

Idadi ya hatua za kitatuzi cha ODE inayotumika kuzalisha akustika kupitia flow matching.

speed_up_factor chaguomsingi 1

Kizidishi cha kasi ya usemi: usemi uliotengenezwa huwa wa polepole chini ya 1.0 na wa haraka juu ya 1.0.

POST /run/tada/3b/text-to-speech?wait=20 makadirio → $ 0.004

# 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/tada/3b/text-to-speech?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",
    "prompt": "Hello from Doitong. This is a short test sentence."
  }'

# 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"

const API = "https://api.doitong.com/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/tada/3b/text-to-speech?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "prompt": "Hello from Doitong. This is a short test sentence."
  }),
});
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.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "prompt": "Hello from Doitong. This is a short test sentence.",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/tada/3b/text-to-speech", 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": "tada/3b/text-to-speech",
      "input": {
        "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
        "prompt": "Hello from Doitong. This is a short test sentence."
      },
      "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 Tada

Hunakili msemaji kutoka klipu ya marejeleo (`audio_url`) na kusoma maandishi ya `prompt` kwa sauti hiyo. Chaguo la `language` linakubali en, ar, ch, de, es, fr, it, ja, pl na pt. Kwa marejeleo yasiyo ya Kiingereza, toa `transcript`, kwa sababu utambuzi uliojengewa ndani ni wa Kiingereza pekee. Kasi inaweza kurekebishwa kutoka 0.5 hadi 2, na matokeo ni wav au mp3.

Vigezo

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

JinaAina ChaguomsingiInaruhusiwa Maelezo

audio_urlinahitajika audio

Ainaurl · audio

Chanzo cha kunakili sauti kilichotolewa kama URL ya faili ya sauti, kinachomtambulisha mzungumzaji ambaye sifa zake za sauti zinapaswa kuigwa na modeli.

transcriptsi lazima

Ainastring

Chaguomsingi

Unukuzi wa sauti ya marejeo ambao lazima utolewe kwa rekodi za lugha nyingine isipokuwa Kiingereza; unukuzi wa kiotomatiki umejengwa kwa Kiingereza pekee.

promptinahitajika

Ainastring

Maudhui ya usemi yaliyotolewa kama maandishi; mzungumzaji wa marejeo hutoa sauti inayotumika kuyatoa.

languagesi lazima

Ainaenum

Chaguomsingien

enarchdeesfritjaplpt

Msimbo wa lugha wa upangaji wa maandishi, ambao lazima ulingane na lugha ya usanisi unapozalisha usemi katika lugha nyingine isipokuwa Kiingereza.

num_extra_stepssi lazima

Ainainteger

Chaguomsingi0

0 – 50

Idadi ya hatua za ziada za autoregressive za kuongeza prosody au ukimya wa mwisho kwa kuendeleza usemi zaidi ya maandishi yaliyotolewa.

temperaturesi lazima

Ainanumber

Chaguomsingi0.6

≤ 2> 0

Halijoto ya sampuli ya tokeni za maandishi: kuiongeza huongeza utofauti wa tokeo, na 0 au chini hairuhusiwi.

top_psi lazima

Ainanumber

Chaguomsingi0.9

0 – 1

Mpangilio wa sampuli wa Top-p (nucleus) unaotumika kuzalisha maandishi.

repetition_penaltysi lazima

Ainanumber

Chaguomsingi1.1

1 – 2

Adhabu ya kurudiwa kwa tokeni wakati wa kuzalisha tokeo.

acoustic_cfg_scalesi lazima

Ainanumber

Chaguomsingi1.6

0 – 10

Nguvu ya mwongozo usio na classifier inayotumika kuzalisha vipengele vya akustika.

noise_temperaturesi lazima

Ainanumber

Chaguomsingi0.9

0 – 2

Halijoto ya kelele inayotumika wakati wa diffusion ya flow-matching.

num_inference_stepssi lazima

Ainainteger

Chaguomsingi20

1 – 50

Idadi ya hatua za kitatuzi cha ODE inayotumika kuzalisha akustika kupitia flow matching.

speed_up_factorsi lazima

Ainanumber

Chaguomsingi1

0.5 – 2

Kizidishi cha kasi ya usemi: usemi uliotengenezwa huwa wa polepole chini ya 1.0 na wa haraka juu ya 1.0.

output_formatsi lazima

Ainaenum

Chaguomsingiwav

wavmp3

Muundo wa faili wa sauti iliyozalishwa.

enable_safety_checkersi lazima

Ainaboolean

Chaguomsingitrue

Ukaguzi unaweza kulegezwa kwa kuweka false, ikiwa mpigaji simu ameidhinishwa.

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": "tada/3b/text-to-speech",
  "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": 4,
    "usd": "0.004",
    "charged": 4,
    "refunded": 0
  },
  "input": {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "prompt": "Hello from Doitong. This is a short test sentence."
  },
  "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,
      "channels": 1,
      "sample_rate": 1,
      "bitrate": "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.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, duration, channels, sample_rate, bitrate}Faili ya sauti iliyo na matamshi yaliyosanisishwa.

Miundo zaidi: Maandishi hadi Matamshi

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/tada/3b/text-to-speech.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt

Tokeo lako la kwanza linaonekana hapa

Unda ombi

Endesha ombi hili

Kuhusu Tada

Vigezo

Tokeo

Tofauti nyingine za Tada

Tada TTS 1B Tofauti: 2

Miundo zaidi: Maandishi hadi Matamshi

Eleven v4 Text to Speech Tofauti: 3

MiniMax Speech 2.8 HD Tofauti: 8

F5 TTS

Async Text to Speech Pro V1.0