# OpenRouter [Audio] API

> Variante gateway LLM che elabora un file audio per trascrizione o analisi, con un prompt

Accetta un file audio tramite `audio_url` insieme a un `prompt` e a un `model` obbligatorio. I formati elencati sono wav, mp3, aiff, aac, ogg, flac e m4a. Sono disponibili impostazioni opzionali `system_prompt`, `temperature`, `max_tokens`, `reasoning` e ricerca web. Restituisce testo e utilizzo dei token.

- Model id: `openrouter/router/audio`
- Made by: OpenRouter
- Category: LLM
- Output: text
- Charged by usage (up to $1.858 per run, typical $0.019; the rest of the hold is refunded): $0.01 / usage unit (cheapest run $0.019 (19 API credits))
- Run: `POST https://api.doitong.com/v1/run/openrouter/router/audio`
- Quote: `POST https://api.doitong.com/v1/quote/openrouter/router/audio`
- Docs page: https://doitong.com/it/developers/models/openrouter/router/audio

## Pricing

Price: **$0.01 / usage unit**. Charged by actual usage at $0.01 / usage unit: up to $1.858 per run (the quote gives the maximum for your input), the rest is refunded automatically after the run. A typical run costs $0.019.

The full example input below holds up to $1.858 = 1858 API credits (up to 185.7946 units × $0.01) when it starts; a typical run costs $0.019 (19 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). This model is charged by usage: `POST https://api.doitong.com/v1/quote/openrouter/router/audio` with the same JSON body returns the most the run can cost for that input (`credits`, debited when the run starts); after the run you pay the usage the model reports and the rest is refunded automatically. An input whose maximum would exceed the per-run limit is refused with 422. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `audio_url` | `audio` | string (audio URL) | yes |  |  | Input audio per l'elaborazione, specificato tramite URL o URI dati. I formati accettati sono m4a, flac, ogg, aac, aiff, mp3 e wav. |
| `prompt` |  | string | yes |  |  | Prompt che dirige l'elaborazione dell'audio. |
| `system_prompt` |  | string \| null | no |  |  | Prompt di sistema che fornisce al modello istruzioni o contesto. |
| `model` |  | string | yes |  |  | Nome che identifica il modello da eseguire. |
| `reasoning` |  | boolean | no | `false` |  | Indica se includere il ragionamento nella risposta finale. |
| `temperature` |  | number | no | `1` | 0 – 2 | Controllo della variabilità della risposta, con 0 che garantisce una risposta identica quando l'input non cambia. Aumentando il valore, le risposte si allontanano da quelle prevedibili e tipiche verso risposte più diversificate e meno comuni. |
| `max_tokens` |  | integer \| null | no |  | ≥ 1 | Limita il numero di token generati della risposta a un valore non superiore alla lunghezza del contesto meno la lunghezza del prompt. La generazione non può superare il limite specificato. |
| `enable_web_search` |  | boolean | no | `false` |  | Interruttore per l'accesso al Web che consente al modello di scegliere se e quando cercare, incluse più ricerche in una singola richiesta. Le ricerche usano lo strumento di ricerca Web lato server di OpenRouter per ottenere informazioni in tempo reale. |
| `web_search_options` |  | object {engine, max_results, max_uses, max_total_results, search_context_size, max_characters, allowed_domains, excluded_domains, user_location} \| null | no |  |  | Configurazione della ricerca Web, inclusa la selezione del motore, i limiti dei risultati e il filtro dei domini. Usata solo quando enable_web_search è true. |
| `web_search_options.engine` |  | enum (string) | no | `auto` | `auto`, `native`, `exa` | Selezione del motore di ricerca: 'auto' e 'native' ricorrono entrambi a Exa quando la ricerca nativa non è disponibile. 'auto' usa la ricerca nativa del provider disponibile; 'native' preferisce la ricerca integrata di OpenAI, Anthropic, Google, xAI o Perplexity. Per usare esclusivamente l'API di ricerca di Exa, seleziona 'exa'. |
| `web_search_options.max_results` |  | integer \| null | no |  | 1 – 25 | Limite dei risultati per ogni chiamata di ricerca Exa, da 1 a 25, con un valore predefinito di 5. La ricerca nativa del provider ignora questa impostazione. |
| `web_search_options.max_uses` |  | integer \| null | no |  | ≥ 1 | Limite di ricerca per richiesta, passato ad Anthropic per la ricerca nativa ma ignorato dagli altri provider nativi. Le chiamate oltre il limite ricevono un risultato di errore e non vengono eseguite. |
| `web_search_options.max_total_results` |  | integer \| null | no |  | ≥ 1 | Limite combinato dei risultati per tutte le ricerche incluse in una richiesta. |
| `web_search_options.search_context_size` |  | enum (string) \| null | no |  | `low`, `medium`, `high` | Quantità recuperata per risultato da Exa, sostituita da max_characters se entrambi sono forniti e ignorata per la ricerca nativa del provider. Scegli low per 5K caratteri, medium per 15K o high per 30K; se non specificata, Exa adatta la quantità a circa 2–4K per risultato. |
| `web_search_options.max_characters` |  | integer \| null | no |  | 1 – 100,000 | Limite di caratteri del contenuto per risultato per Exa, che sostituisce search_context_size se entrambe le impostazioni sono fornite. Imposta un massimo esatto da 1 a 100.000 caratteri; la ricerca nativa del provider ignora questa impostazione. |
| `web_search_options.allowed_domains` |  | array of string \| null | no |  |  | Elenco dei domini consentiti per Exa e per la maggior parte dei provider di ricerca nativi, che limita i risultati ai domini elencati. La ricerca nativa di Google non lo supporta. |
| `web_search_options.excluded_domains` |  | array of string \| null | no |  |  | Elenco dei domini esclusi per le ricerche Exa e i provider nativi compatibili; le ricerche native di Google e OpenAI non possono applicarlo. I risultati provenienti dai domini elencati vengono esclusi. |
| `web_search_options.user_location` |  | object {type, city, region, country, timezone} \| null | no |  |  | Posizione approssimativa dell'utente che orienta geograficamente i risultati della ricerca nativa; Exa non usa queste informazioni. |
| `web_search_options.user_location.type` |  | string | no | `approximate` |  | Classificazione della posizione; l'unico valore supportato è 'approximate'. |
| `web_search_options.user_location.city` |  | string \| null | no |  |  | Nome della città, ad esempio 'San Francisco'. |
| `web_search_options.user_location.region` |  | string \| null | no |  |  | Nome dello stato o della regione, ad esempio 'California'. |
| `web_search_options.user_location.country` |  | string \| null | no |  |  | Identificatore del paese espresso come due lettere, ad esempio 'US'. |
| `web_search_options.user_location.timezone` |  | string \| null | no |  |  | Identificatore del fuso orario nella notazione IANA, ad esempio 'America/Los_Angeles'. |

File parameters (`audio`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "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",
  "model": "google/gemini-3.8-flash"
}
```

A fuller example:

```json
{
  "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",
  "model": "google/gemini-3.8-flash"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# 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/openrouter/router/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_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "model": "google/gemini-3.8-flash"
  }'

# 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"
```

### JavaScript

```javascript
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/openrouter/router/audio?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "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",
    "model": "google/gemini-3.8-flash"
  }),
});
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 + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "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",
    "model": "google/gemini-3.8-flash",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/openrouter/router/audio", 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"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "openrouter/router/audio",
      "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",
        "model": "google/gemini-3.8-flash"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "openrouter/router/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": 1858,
    "usd": "1.858",
    "charged": 1858,
    "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",
    "model": "google/gemini-3.8-flash"
  },
  "output": {
    "output": "The audio contains a conversation between two people discussing the weather forecast for the upcoming week.",
    "usage": {
      "prompt_tokens": 1,
      "completion_tokens": 1,
      "total_tokens": 0,
      "cost": 1.0,
      "prompt_tokens_details": {
        "cached_tokens": 0,
        "cache_write_tokens": 0
      }
    }
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "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"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `output` | string | Risultato prodotto dall'elaborazione dell'audio. |
| `usage` | object {prompt_tokens, completion_tokens, total_tokens, cost, prompt_tokens_details} \| null | Dettagli sul consumo di token. |

## Related models

- [OpenRouter](https://doitong.com/developers/models/openrouter/router.md) (`openrouter/router`): $0.01 / usage unit
- [OpenRouter \[Enterprise\]](https://doitong.com/developers/models/openrouter/router/enterprise.md) (`openrouter/router/enterprise`): $0.01 / usage unit
- [OpenRouter \[Video\]](https://doitong.com/developers/models/openrouter/router/video.md) (`openrouter/router/video`): $0.01 / usage unit
- [OpenRouter \[Video\]\[Enterprise\]](https://doitong.com/developers/models/openrouter/router/video/enterprise.md) (`openrouter/router/video/enterprise`): $0.01 / usage unit
- [OpenRouter \[Vision\]](https://doitong.com/developers/models/openrouter/router/vision.md) (`openrouter/router/vision`): $0.01 / usage unit
- [Bytedance Seed V2 Mini](https://doitong.com/developers/models/bytedance/seed/v2/mini.md) (`bytedance/seed/v2/mini`): $0.0001 / 1000 tokens
- [Fibo Edit \[Structured Instruction\]](https://doitong.com/developers/models/bria/fibo-edit/edit/structured_instruction.md) (`bria/fibo-edit/edit/structured_instruction`): $0.01 / request
- [Fibo Lite · Structured Prompt](https://doitong.com/developers/models/bria/fibo-lite/generate/structured_prompt.md) (`bria/fibo-lite/generate/structured_prompt`): $0.008 / request

## Links

- HTML page: https://doitong.com/developers/models/openrouter/router/audio
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=openrouter/router/audio
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/openrouter/router/audio