---
title: Dia2 2B | Runware Docs
url: https://runware.ai/docs/models/dia2-2b
description: Streaming dialogue TTS with voice cloning, non-verbal cues, and multi-speaker support
---
# Dia2 2B

![Dia2 2B](https://assets.runware.ai/covers/dia2-2b.jpg)

Dia2 2B is a 2 billion parameter streaming text-to-speech model from Nari Labs designed for real-time conversational AI. It begins generating audio immediately from partial text input, supports multi-speaker dialogue via speaker tags, voice cloning from a few seconds of reference audio, and non-verbal cues like laughter, sighs, and coughs. Released under Apache 2.0 for commercial use.

- **Status**: live
- **ID**: `runware:dia2@2b`
- Try in Playground
- **Release Date**: November 19, 2025
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Audio, Audio to Audio, Checkpoint

## Pricing

$0.00675 from, per run · ~26s per request

**Measured runs**

- speech.text Welcome aboard. Today we will explore clear, natural conversational speech. · 10s audio: `$0.00675` (~4s)
- speech.text Welcome aboard. Today we will explore how clear, natural speech can make a conversation feel warm, useful, and easy to follow. The system should speak at a steady pace, pause naturally between ideas, and keep every sentence understandable. Imagine that this message is part of a helpful daily briefing for someone preparing for work. It includes a friendly greeting, a short explanation, and a calm conclusion. Along the way, the voice can vary its rhythm slightly without becoming dramatic. Thank you for listening, and we hope the rest of your day is productive, relaxed, and full of good moments ahead. · 10s audio: `$0.0312` (~17s)
- speech.text Welcome aboard. Today we will explore how clear, natural speech can make a conversation feel warm, useful, and easy to follow. The system should speak at a steady pace, pause naturally between ideas, and keep every sentence understandable. Imagine that this message is part of a helpful daily briefing for someone preparing for work. It includes a friendly greeting, a short explanation, and a calm conclusion. Along the way, the voice can vary its rhythm slightly without becoming dramatic. Thank you for listening, and we hope the rest of your day is productive, relaxed, and full of good moments ahead. Welcome aboard. Today we will explore how clear, natural speech can make a conversation feel warm, useful, and easy to follow. The system should speak at a steady pace, pause naturally between ideas, and keep every sentence understandable. Imagine that this message is part of a helpful daily briefing for someone preparing for work. It includes a friendly greeting, a short explanation, and a calm conclusion. Along the way, the voice can vary its rhythm slightly without becoming dramatic. Thank you for listening, and we hope the rest of your day is productive, relaxed, and full of good moments ahead. Welcome aboard. Today we will explore how clear, natural speech can make a conversation feel warm, useful, and easy to follow. The system should speak at a steady pace, pause naturally between ideas, and keep every sentence understandable. Imagine that this message is part of a helpful daily briefing for someone preparing for work. It includes a friendly greeting, a short explanation, and a calm conclusion. Along the way, the voice can vary its rhythm slightly without becoming dramatic. Thank you for listening, and we hope the rest of your day is productive, relaxed, and full of good moments ahead. Welcome aboard. Today we will explore how clear, natural speech can make a conversation feel warm, useful, and easy to follow. The system should speak at a steady pace, pause naturally between ideas, and keep every sentence understandable. Imagine that this message is part of a helpful daily briefing for someone preparing for work. It includes a friendly greeting, a short explanation, and a calm conclusion. Along the way, the voice can vary its rhythm slightly without becoming dramatic. Thank you for listening, and we hope the rest of your day is productive, relaxed, and full of good moments ahead. · 10s audio: `$0.101` (~49s)

**4 example generations**

- [text-to-audio](https://runware.ai/docs/models/dia2-2b/examples#example-alpine-apiary-podcast-stinger): `$0.0048` (~14s)
- [text-to-audio](https://runware.ai/docs/models/dia2-2b/examples#example-rare-film-archive-podcast-opening): `$0.0163` (~26s)
- [multi-speaker-dialogue](https://runware.ai/docs/models/dia2-2b/examples#example-electric-ferry-vocal-brand-stinger): `$0.0211` (~31s)
- [voice-cloning](https://runware.ai/docs/models/dia2-2b/examples#example-mushroom-farm-biosecurity-module-narration): `$0.0355` (~52s)

billed by compute time, so a request costs what it took · times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

When `settings.includePrefix` is provided, `inputs.audios` is required.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/dia2-2b#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `audioInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/dia2-2b#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/dia2-2b#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Audio output type.

**Allowed values**: `URL` `base64Data` `dataURI`

### [outputFormat](https://runware.ai/docs/models/dia2-2b#request-outputformat)

- **Type**: `string`
- **Default**: `MP3`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`MP3\`: Compressed audio, smaller file size.
- \`WAV\`: Uncompressed, high-quality audio.
- \`FLAC\`: Lossless compression.
- \`OGG\`: Open-source compressed audio format (Vorbis codec).

**Allowed values**: `MP3` `WAV` `FLAC` `OGG`

### [audioSettings](https://runware.ai/docs/models/dia2-2b#request-audiosettings)

- **Path**: `audioSettings.bitrate`
- **Type**: `object (3 properties)`

Audio encoding settings for controlling the bitrate, number of channels, and sample rate of the generated audio. Only applicable for lossy output formats (`MP3` and `OGG`). When using lossless formats (`WAV` or `FLAC`), this parameter must not be provided.

The available sample rates and valid bitrate ranges depend on the output format. For `OGG`, bitrate limits also vary by the number of channels.

**MP3 bitrate limits**:

Bitrate limits for MP3 are the same regardless of mono or stereo.

| Sample Rate | Min Bitrate | Max Bitrate |
| --- | --- | --- |
| 8,000 Hz | 8 kbps | 64 kbps |
| 11,025 Hz | 8 kbps | 64 kbps |
| 12,000 Hz | 8 kbps | 64 kbps |
| 16,000 Hz | 8 kbps | 160 kbps |
| 22,050 Hz | 8 kbps | 160 kbps |
| 24,000 Hz | 8 kbps | 160 kbps |
| 32,000 Hz | 32 kbps | 320 kbps |
| 44,100 Hz | 32 kbps | 320 kbps |
| 48,000 Hz | 32 kbps | 320 kbps |

**OGG bitrate limits — Mono (1 channel)**:

| Sample Rate | Min Bitrate | Max Bitrate |
| --- | --- | --- |
| 8,000 Hz | 8 kbps | 40 kbps |
| 12,000 Hz | 16 kbps | 48 kbps |
| 16,000 Hz | 16 kbps | 96 kbps |
| 24,000 Hz | 16 kbps | 80 kbps |
| 48,000 Hz | 32 kbps | 224 kbps |

**OGG bitrate limits — Stereo (2 channels)**:

| Sample Rate | Min Bitrate | Max Bitrate |
| --- | --- | --- |
| 8,000 Hz | 16 kbps | 80 kbps |
| 12,000 Hz | 16 kbps | 96 kbps |
| 16,000 Hz | 24 kbps | 192 kbps |
| 24,000 Hz | 32 kbps | 160 kbps |
| 48,000 Hz | 48 kbps | 256 kbps |

> [!NOTE]
> **Lossless formats**: When `outputFormat` is set to `WAV` or `FLAC`, the `audioSettings` parameter is not available since these formats produce uncompressed or lossless audio with no configurable encoding settings.

#### [bitrate](https://runware.ai/docs/models/dia2-2b#request-audiosettings-bitrate)

- **Path**: `audioSettings.bitrate`
- **Type**: `integer`
- **Min**: `8`

Audio bitrate in kbps.

#### [channels](https://runware.ai/docs/models/dia2-2b#request-audiosettings-channels)

- **Path**: `audioSettings.channels`
- **Type**: `integer`
- **Default**: `2`

Number of audio channels. 1 for mono, 2 for stereo.

**Allowed values**: `1` `2`

#### [sampleRate](https://runware.ai/docs/models/dia2-2b#request-audiosettings-samplerate)

- **Path**: `audioSettings.sampleRate`
- **Type**: `integer`

Audio sample rate in Hz.

### [webhookURL](https://runware.ai/docs/models/dia2-2b#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/dia2-2b#request-deliverymethod)

- **Type**: `string`
- **Default**: `sync`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/dia2-2b#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [ttl](https://runware.ai/docs/models/dia2-2b#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/dia2-2b#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/dia2-2b#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `4`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [audios](https://runware.ai/docs/models/dia2-2b#request-inputs-audios)

- **Path**: `inputs.audios`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `2`

Voice reference audio samples for speaker cloning (UUID, URL, or Base64). The first audio provides the voice for lines tagged \[S1\] in speech.text, and the second for \[S2\]. Internally transcribed with Whisper for alignment.

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/dia2-2b#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `runware:dia2@2b`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [negativePrompt](https://runware.ai/docs/models/dia2-2b#request-negativeprompt)

- **Type**: `string`
- **Min**: `2`
- **Max**: `3000`

Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).

**Learn more** (1 resource):

- [Prompts: Negative Prompts](https://runware.ai/docs/learn/prompts#negative-prompts) (learn)

### [seed](https://runware.ai/docs/models/dia2-2b#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `2147483647`

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

### [CFGScale](https://runware.ai/docs/models/dia2-2b#request-cfgscale)

- **Type**: `float`
- **Min**: `1`
- **Max**: `30`
- **Step**: `0.01`
- **Default**: `3`

Guidance scale representing how closely the output will resemble the prompt. Higher values produce results more aligned with the prompt.

**Learn more** (1 resource):

- [Cfg Scale](https://runware.ai/docs/learn/cfg-scale) (learn)

### [speech](https://runware.ai/docs/models/dia2-2b#request-speech)

- **Path**: `speech.text`
- **Type**: `object (1 property)`
- **Required**: true

Settings for speech generation.

#### [text](https://runware.ai/docs/models/dia2-2b#request-speech-text)

- **Path**: `speech.text`
- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `3000`

Text to convert to speech.

**Settings**

Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object.

### [temperature](https://runware.ai/docs/models/dia2-2b#request-settings-temperature)

- **Path**: `settings.temperature`
- **Type**: `float`
- **Min**: `0`
- **Max**: `5`
- **Default**: `0.6`

Sampling temperature for text token generation. Lower = more coherent, higher = more variety. 0 = greedy decoding.

### [audioTemperature](https://runware.ai/docs/models/dia2-2b#request-settings-audiotemperature)

- **Path**: `settings.audioTemperature`
- **Type**: `float`
- **Min**: `0`
- **Max**: `5`
- **Default**: `0.8`

Sampling temperature for audio token generation. Lower = cleaner audio, higher = more expressive. 0 = greedy decoding.

### [includePrefix](https://runware.ai/docs/models/dia2-2b#request-settings-includeprefix)

- **Path**: `settings.includePrefix`
- **Type**: `boolean`

Whether to include prefix audio in the final output or trim it.

### [topK](https://runware.ai/docs/models/dia2-2b#request-settings-topk)

- **Path**: `settings.topK`
- **Type**: `integer`
- **Min**: `1`
- **Max**: `500`
- **Default**: `50`

Top-K sampling for both text and audio tokens. Limits selection to K most likely tokens per step.

## Response Parameters

### [taskType](https://runware.ai/docs/models/dia2-2b#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `audioInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/dia2-2b#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [audioUUID](https://runware.ai/docs/models/dia2-2b#response-audiouuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output audio.

### [audioURL](https://runware.ai/docs/models/dia2-2b#response-audiourl)

- **Type**: `string`
- **Format**: `uri`

URL of the output audio.

### [audioBase64Data](https://runware.ai/docs/models/dia2-2b#response-audiobase64data)

- **Type**: `string`

Base64-encoded audio data.

### [audioDataURI](https://runware.ai/docs/models/dia2-2b#response-audiodatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output audio.

### [seed](https://runware.ai/docs/models/dia2-2b#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [cost](https://runware.ai/docs/models/dia2-2b#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### text-to-audio (text-to-audio)

[Listen to audio](https://assets.runware.ai/examples/dia2-2b/083dc3b8-49f3-4f67-8373-679510b71097.mp3)

> **Prompt**: [S1] The can arrived without a title—just a strip of yellow tape and three handwritten words: “Do not project.” Inside was a nitrate film from 1931, brittle as an autumn leaf... and possibly the only surviving record of a vanished coastal town. (soft sigh) But opening the can started a clock. Nitrate decays, and when it goes, it can take an entire archive with it. So the conservators had one night to identify the images, stabilize the reel, and decide what could still be saved. I’m Mara Venn, and this is The Last Copy—a podcast about fragile media, patient hands, and the race to preserve our memory before it disappears.

```json
{
  "taskType": "audioInference",
  "taskUUID": "3154c851-4501-4760-9d79-cc164c141048",
  "model": "runware:dia2@2b",
  "speech": {
    "text": "[S1] The can arrived without a title—just a strip of yellow tape and three handwritten words: “Do not project.” Inside was a nitrate film from 1931, brittle as an autumn leaf... and possibly the only surviving record of a vanished coastal town. (soft sigh) But opening the can started a clock. Nitrate decays, and when it goes, it can take an entire archive with it. So the conservators had one night to identify the images, stabilize the reel, and decide what could still be saved. I’m Mara Venn, and this is The Last Copy—a podcast about fragile media, patient hands, and the race to preserve our memory before it disappears."
  }
}
```

---

### text-to-audio (text-to-audio)

[Listen to audio](https://assets.runware.ai/examples/dia2-2b/bd3245a7-daf2-4e28-b2a9-1257cc19c945.mp3)

> **Prompt**: [S1] Listen closely... that hum is a whole city waking up. Welcome to The Alpine Apiary—where beekeepers share hard-won wisdom, one buzzing frame at a time.

```json
{
  "taskType": "audioInference",
  "taskUUID": "8ce8b4ba-0c15-42c1-b5cd-1739aac31650",
  "model": "runware:dia2@2b",
  "speech": {
    "text": "[S1] Listen closely... that hum is a whole city waking up. Welcome to The Alpine Apiary—where beekeepers share hard-won wisdom, one buzzing frame at a time."
  }
}
```

---

### voice-cloning (voice-cloning)

[Listen to audio](https://assets.runware.ai/examples/dia2-2b/bdc9936b-b200-4399-b220-b8e0fd20005a.mp3)

> **Prompt**: [S1] Before entering a growing room, stop at the hygiene station. Remove visible soil from your boots, step through the disinfectant tray, and sanitize both hands. Always move from younger, cleaner crops toward older crops—never in the opposite direction. If you notice green mold, unusual spotting, or a sour odor, do not touch the affected bed. Mark the location, leave the room, and report it to the crop supervisor. Tools, picking knives, and harvest crates must remain assigned to their designated room unless they have completed the full cleaning cycle. These small steps protect the crop, reduce cross-contamination, and help keep every growing room productive.

```json
{
  "taskType": "audioInference",
  "taskUUID": "f0105629-fa57-435d-bdde-3970802745ae",
  "model": "runware:dia2@2b",
  "speech": {
    "text": "[S1] Before entering a growing room, stop at the hygiene station. Remove visible soil from your boots, step through the disinfectant tray, and sanitize both hands. Always move from younger, cleaner crops toward older crops—never in the opposite direction. If you notice green mold, unusual spotting, or a sour odor, do not touch the affected bed. Mark the location, leave the room, and report it to the crop supervisor. Tools, picking knives, and harvest crates must remain assigned to their designated room unless they have completed the full cleaning cycle. These small steps protect the crop, reduce cross-contamination, and help keep every growing room productive."
  },
  "inputs": {
    "audios": [
      "https://assets.runware.ai/assets/inputs/a7687dfd-efee-4118-a86d-bda55fd55100.mp3"
    ]
  }
}
```

---

### multi-speaker-dialogue (multi-speaker-dialogue)

[Listen to audio](https://assets.runware.ai/examples/dia2-2b/09bd4182-28f3-40b4-afe8-cab5dfdb4742.mp3)

> **Prompt**: [S1] Hear that? [S2] Exactly. [S1] No engine roar. [S2] Just the harbor. [S1] Northline Electric Ferry. [S2] Move with the tide.

```json
{
  "taskType": "audioInference",
  "taskUUID": "b9d31689-2e8c-470d-8c3e-712bdd748760",
  "model": "runware:dia2@2b",
  "speech": {
    "text": "[S1] Hear that?\n[S2] Exactly.\n[S1] No engine roar.\n[S2] Just the harbor.\n[S1] Northline Electric Ferry.\n[S2] Move with the tide."
  },
  "inputs": {
    "audios": [
      "https://assets.runware.ai/assets/inputs/0c3cfc65-6316-49e3-af36-56c28dfaa310.mp3",
      "https://assets.runware.ai/assets/inputs/f10a95ca-029f-43ab-a4d1-408e8bd7b098.mp3"
    ]
  }
}
```