Skip to content

Personaplex

Integrate

Model id personaplex
# 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/personaplex?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.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Files like the example: $0.01 10 API credits · ≈ ₽1.05 your files are measured before the run Run it on this page

Get API key
NVIDIA Audio #audio

Speech-to-speech conversational model that answers spoken audio in a persona and voice you choose

NVIDIA · Audio

Your first result goes here

Build a request below and run it with your API key. Outputs are copied to our storage, kept forever or 7 days for free.

Build a request

Controls are generated from the model schema. The code and the price update as you change them.

default You are a wise and fr...

Text prompt defining the AI's persona and the context of the conversation.

Drop a file, or

Voice-cloning sample URL; clear speech lasting at least 10 seconds is recommended. The sample is cloned on the fly, replacing the preset 'voice' for the AI's response.

•required audio_url
Drop a file, or

URL of the audio input containing the user's speech.

Advanced voice · temperature_audio · temperature_text · top_k_audio · top_k_text · seed · enable_safety_checker
default NATF2

AI response voice ID, overridden by voice_audio_url when supplied. Its codes distinguish natural (NAT) from variety (VAR) and female (F) from male (M).

default 0.8

Temperature used when sampling audio; increasing it yields more varied results.

default 0.7

Temperature used when sampling text; increasing it yields more varied results.

default 250

Top-K setting used to sample audio tokens.

default 25

Top-K setting used to sample text tokens.

Seed controlling randomness for reproducible results.

POST /run/personaplex?wait=20 quote → $0.01
# 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/personaplex?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.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Run this request

Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key

About Personaplex

Receives a user's speech through `audio_url` and replies with generated speech, returned along with a transcript of the reply and its duration. A text `prompt` defines the persona, and `voice` selects a preset. Alternatively `voice_audio_url` clones a voice from a sample, where 10 or more seconds of clear speech is recommended. Sampling is tunable through temperature and top-k settings.

Parameters

Send either the canonical name or the native name, not both. Canonical names

NameType DefaultAllowed Description
promptoptional
Typestring
DefaultYou are a wise and friendly teacher. Answer questions or provide advice in a clear and engaging way.
Text prompt defining the AI's persona and the context of the conversation.
voiceoptional
Typeenum
DefaultNATF2
NATF0NATF1NATF2NATF3NATM0NATM1NATM2NATM3VARF0VARF1VARF2VARF3VARF4VARM0VARM1VARM2
+2 moreVARM3VARM4
AI response voice ID, overridden by voice_audio_url when supplied. Its codes distinguish natural (NAT) from variety (VAR) and female (F) from male (M).
voice_audio_urloptional
Typeurl · audio
Voice-cloning sample URL; clear speech lasting at least 10 seconds is recommended. The sample is cloned on the fly, replacing the preset 'voice' for the AI's response.
temperature_audiooptional
Typenumber
Default0.8
0 – 2
Temperature used when sampling audio; increasing it yields more varied results.
temperature_textoptional
Typenumber
Default0.7
0 – 2
Temperature used when sampling text; increasing it yields more varied results.
top_k_audiooptional
Typeinteger
Default250
1 – 2,048
Top-K setting used to sample audio tokens.
top_k_textoptional
Typeinteger
Default25
1 – 1,000
Top-K setting used to sample text tokens.
seedoptional
Typeinteger | null
Seed controlling randomness for reproducible results.
audio_urlrequired audio
Typeurl · audio
URL of the audio input containing the user's speech.
enable_safety_checkeroptional
Typeboolean
Defaulttrue
Screening can be relaxed by setting false, provided the caller is authorized.
required Canonical name, also accepted

File parameters take a public https:// URL, a data: URI up to 10 MB, or the file_url of an upload. Files

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "personaplex",
  "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": 10,
    "usd": "0.01",
    "charged": 10,
    "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
    },
    "text": " Thank you for calling SwiftPlex Appliances. This is Farhod, how can I help you today? I understand your concern. The replacement part is out of stock, so we can't ship it right away. We can use an alternative part that will arrive in 3 days. Would you like to proceed with that?",
    "duration": 5,
    "seed": 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"
  }
}
Your files, your choiceEvery outputs[].url is a copy on our storage: kept forever (paid per GB-month) or 7 days for free, by your account setting or ?storage=.
Same shape on every modeltype, url, content_type, width, height and duration, for images, video and audio alike. output is the model’s own result object.
Fields of output
audio
object {url, content_type, file_name, file_size}AI-generated response audio in WAV format at 24 kHz.
text
stringText transcription of the response from the AI.
duration
numberLength of the generated audio, measured in seconds.
seed
integerSeed value applied during generation.

More models: Audio

For AI agents: this page as Markdown is at https://doitong.com/en-US/developers/models/personaplex.md. All models and guides: https://doitong.com/developers/llms.txt