## Basic model info

- Model name: fish-audio/fish-audio drama-3
- Model description: Fish Audio Drama 3: expressive text-to-speech you direct in plain language. Put bracketed direction such as [nervous, whispering] before a line or use tags like <whisper>; 83 languages; pick any voice from the Fish Audio voice library by voice_id.
- Endpoint name: text-to-speech


## Model schema

The model schema is defined in the OpenAPI schema: [OpenAPI Schema](https://oapi.sunra.ai/main/fish-audio/drama-3/latest.json)

### Model input schema

The model input schema is:



```json
{
  "properties": {
    "output_format": {
      "default": "mp3",
      "description": "Output audio format. WAV is wrapped from OpenRouter's raw 44.1 kHz mono PCM.",
      "enum": [
        "mp3",
        "wav"
      ],
      "title": "Output Format",
      "type": "string",
      "x-sr-order": 401
    },
    "text": {
      "description": "Text to synthesize, up to 10,000 UTF-8 bytes. Drama 3 accepts bracketed directions such as `[nervous, whispering]` and scoped tags such as `<whisper>...</whisper>`. OpenRouter's measured hard ceiling is 50 MiB for the complete serialized request body.",
      "minLength": 1,
      "title": "Text",
      "type": "string",
      "x-sr-order": 201
    },
    "voice_id": {
      "anyOf": [
        {
          "minLength": 1,
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "Optional Fish Audio public voice-library ID. Find IDs in https://fish.audio/discovery/ or in a voice page URL such as https://fish.audio/m/<voice-id>. When omitted, Fish Audio chooses its default voice.",
      "title": "Voice Id",
      "x-sr-order": 301
    }
  },
  "required": [
    "text"
  ],
  "title": "TextToSpeechInput",
  "type": "object"
}
```



### Model output schema

The model output schema is:



```json
{
  "properties": {
    "audio": {
      "properties": {
        "content_type": {
          "description": "The mime type of the file.",
          "title": "Content Type",
          "type": "string"
        },
        "file_name": {
          "description": "The name of the file. It will be auto-generated if not provided.",
          "title": "File Name",
          "type": "string"
        },
        "file_size": {
          "description": "The size of the file in bytes.",
          "title": "File Size",
          "type": "integer"
        },
        "url": {
          "description": "The URL where the file can be downloaded from.",
          "title": "Url",
          "type": "string"
        }
      },
      "required": [
        "content_type",
        "file_name",
        "file_size",
        "url"
      ],
      "title": "SunraFile",
      "type": "object"
    },
    "input_bytes": {
      "description": "UTF-8 input bytes billed by OpenRouter.",
      "minimum": 1,
      "title": "Input Bytes",
      "type": "integer"
    }
  },
  "required": [
    "audio",
    "input_bytes"
  ],
  "title": "Drama3Output",
  "type": "object"
}
```



## Example inputs and outputs

Use the following example inputs and outputs to understand the model.

### Input example



```json
{
  "output_format": "mp3",
  "text": "",
  "voice_id": null
}
```



### Output example



```json
{
}
```



## Model code examples

### JavaScript



```javascript
import { sunra } from "@sunra/client";

const result = await sunra.subscribe("fish-audio/drama-3/text-to-speech", {
  input: {
  	text: '',
  	voice_id: null,
  	output_format: 'mp3'
  },
  logs: true,
  onQueueUpdate: (update) => {
    console.log(`Status Update: ${update.status}, Request ID: ${update.request_id}`);
  },
});
console.log(result.data);
console.log(result.requestId);
```



### Python



```python
import sunra_client

result = sunra_client.subscribe(
    "fish-audio/drama-3/text-to-speech",
    arguments={
        "text": "",
        "voice_id": None,
        "output_format": "mp3"
    },

    with_logs=True,
    on_enqueue=print,
    on_queue_update=print,
)
print(result)
```



### Java



```java
import ai.sunra.client.*;
import java.util.Map;
import com.google.gson.JsonObject;

var client = SunraClient.withEnvCredentials();

var response = client.subscribe(
    "fish-audio/drama-3/text-to-speech",
    SubscribeOptions.<JsonObject>builder()
        .input(Map.of(
            "text", "",
            "voice_id", null,
            "output_format", "mp3"))

        .resultType(JsonObject.class)
        .onQueueUpdate(update -> System.out.printf(
            "\nStatus Update: %s, Request ID: %s%n",
            update.getStatus(),
            update.getRequestId()
        ))
        .logs(true)
        .build()
);

System.out.println("Completed!");
System.out.println(response.getData());
  
```



### Kotlin



```kotlin
import ai.sunra.client.kt.*
import com.google.gson.JsonObject

val client = createSunraClient()

val response = client.subscribe<JsonObject>(
    endpointId = "fish-audio/drama-3/text-to-speech",
    input = mapOf(
            "text" to "",
            "voice_id" to null,
            "output_format" to "mp3"),
    options = ai.sunra.client.kt.SubscribeOptions(logs = true),
    onUpdate = { update ->
        println("\nStatus Update: ${update.status}, Request ID: ${update.requestId}")
    }
)

println("Completed!")
println(response.data)
  
```



### Curl



```bash

curl --request POST \
  --url https://api.sunra.ai/v1/queue/fish-audio/drama-3/text-to-speech \
  --header "Authorization: Key $SUNRA_KEY" \
  --header "Content-Type: application/json" \
  --data '{"text":"","voice_id":null,"output_format":"mp3"}'
    
```



## Model readme

undefined