# Speech 2.5 HD Preview

{% columns %}
{% column width="66.66666666666666%" %}
{% hint style="info" %}
This documentation is valid for the following list of our models:

* `minimax/speech-2-5-hd-preview`
  {% endhint %}
  {% endcolumn %}

{% column width="33.33333333333334%" %} <a href="https://aimlapi.com/app/minimax/speech-2-5-hd-preview" class="button primary">Try in Playground</a>
{% endcolumn %}
{% endcolumns %}

A high-definition text-to-speech model with enhanced multilingual expressiveness, more precise voice replication, and expanded support for 40 languages.

## Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our [Quickstart guide](https://docs.aimlapi.com/quickstart/setting-up).

## API Schema

## POST /v1/tts

>

```json
{"openapi":"3.0.0","info":{"title":"AIML API","version":"1.0.0"},"servers":[{"url":"https://api.aimlapi.com"}],"paths":{"/v1/tts":{"post":{"operationId":"_v1_tts","requestBody":{"required":true,"content":{"application/json":{"schema":{"type":"object","properties":{"model":{"type":"string","enum":["minimax/speech-2.5-hd-preview"]},"text":{"type":"string","minLength":1,"maxLength":5000,"description":"The text content to be converted to speech."},"voice_setting":{"type":"object","properties":{"voice_id":{"anyOf":[{"type":"string","enum":["Wise_Woman","Friendly_Person","Inspirational_girl","Deep_Voice_Man","Calm_Woman","Casual_Guy","Lively_Girl","Patient_Man","Young_Knight","Determined_Man","Lovely_Girl","Decent_Boy","Imposing_Manner","Elegant_Man","Abbess","Sweet_Girl_2","Exuberant_Girl"]},{"type":"string","minLength":1,"maxLength":64}],"default":"Wise_Woman","description":"A predefined system voice for text-to-speech synthesis."},"speed":{"type":"number","minimum":0.5,"maximum":2,"default":1,"description":"Adjusts the speed of the voice. A value of 1.0 is the default speed, while values less than 1.0 slow down the speech, and values greater than 1.0 speed it up."},"vol":{"type":"number","minimum":0.01,"maximum":10,"default":1,"description":"The volume of the generated speech. Range: (0, 10]. Larger values indicate larger volumes."},"pitch":{"type":"number","minimum":-12,"maximum":12,"default":0,"description":"The pitch of the generated speech. Range: [-12, 12]. 0 = default voice output."},"emotion":{"type":"string","enum":["happy","sad","angry","fearful","disgusted","surprised","neutral"],"description":"Emotional tone to apply to the synthesized speech. Controls the emotional expression of the generated voice output."},"text_normalization":{"type":"boolean","default":false,"description":"English text normalization support. Improves number-reading but increases latency."}},"default":{"voice_id":"Wise_Woman"},"description":"Voice settings overriding stored settings for the given voice. They are applied only on the given request."},"audio_setting":{"type":"object","properties":{"sample_rate":{"type":"integer","description":"Audio sample rate in Hz.","enum":[8000,16000,22050,24000,32000,44100],"default":"32000"},"bitrate":{"type":"integer","description":"Audio bitrate in bits per second. Controls the compression level and audio quality. Higher bitrates provide better quality but larger file sizes.","enum":[32000,64000,128000,256000],"default":"128000"},"format":{"type":"string","enum":["mp3","pcm","flac"],"default":"mp3","description":"Audio output format. MP3 provides good compression and compatibility, PCM offers uncompressed high quality, and FLAC provides lossless compression."},"channel":{"type":"integer","description":"Number of audio channels. 1 for mono (single channel), 2 for stereo (dual channel) output.","enum":[1,2],"default":"1"}},"description":"Audio output configuration"},"pronunciation_dict":{"type":"object","properties":{"tone":{"type":"array","items":{"type":"string"},"description":"Replacement of text and pronunciations. Format: [\"燕少飞/(yan4)(shao3)(fei1)\", \"达菲/(da2)(fei1)\", \"omg/oh my god\"]"}},"required":["tone"],"description":"Custom pronunciation dictionary for handling specific words or phrases. Allows fine-tuning of how certain text should be pronounced using phonetic representations."},"timbre_weights":{"type":"array","items":{"type":"object","properties":{"voice_id":{"anyOf":[{"type":"string","enum":["Wise_Woman","Friendly_Person","Inspirational_girl","Deep_Voice_Man","Calm_Woman","Casual_Guy","Lively_Girl","Patient_Man","Young_Knight","Determined_Man","Lovely_Girl","Decent_Boy","Imposing_Manner","Elegant_Man","Abbess","Sweet_Girl_2","Exuberant_Girl"]},{"type":"string","minLength":1,"maxLength":64}],"description":"A predefined system voice for text-to-speech synthesis."},"weight":{"type":"integer","minimum":1,"maximum":100,"description":"Weight for voice mixing. Range: [1, 100]. Higher weights are sampled more heavily."}},"required":["voice_id","weight"]},"maxItems":4,"description":"Voice mixing configuration allowing combination of up to 4 different voices with specified weights. Each voice contributes to the final output based on its weight value (1-100)."},"language_boost":{"type":"string","enum":["Chinese","Chinese,Yue","English","Arabic","Russian","Spanish","French","Portuguese","German","Turkish","Dutch","Ukrainian","Vietnamese","Indonesian","Japanese","Italian","Korean","Thai","Polish","Romanian","Greek","Czech","Finnish","Hindi","Bulgarian","Danish","Hebrew","Malay","Persian","Slovak","Swedish","Croatian","Filipino","Hungarian","Norwegian","Slovenian","Catalan","Nynorsk","Tamil","Afrikaans","auto"],"description":"Language recognition enhancement option."},"voice_modify":{"type":"object","properties":{"pitch":{"type":"integer","minimum":-100,"maximum":100,"description":"Pitch level (-100 to 100)"},"intensity":{"type":"integer","minimum":-100,"maximum":100,"description":"Intensity level (-100 to 100)"},"timbre":{"type":"integer","minimum":-100,"maximum":100,"description":"Timbre level (-100 to 100)"},"sound_effects":{"type":"string","enum":["spacious_echo","auditorium_echo","lofi_telephone","robotic"],"description":"Audio effects to apply to the synthesized speech. Includes options like spacious_echo, auditorium_echo, lofi_telephone, and robotic effects."}},"description":"Voice modification settings for adjusting pitch, intensity, timbre, and applying sound effects to customize the voice characteristics."},"subtitle_enable":{"type":"boolean","default":false,"description":"Enable subtitle generation service. Only available for non-streaming requests. Generates timing information for the synthesized speech."},"stream":{"type":"boolean","enum":[false],"default":false}},"required":["model","text"],"title":"minimax/speech-2.5-hd-preview"}}}},"responses":{"200":{"content":{"application/json":{"schema":{"type":"object","properties":{"audio":{"type":"string","format":"uri"},"meta":{"type":"object","nullable":true,"properties":{"usage":{"type":"object","nullable":true,"properties":{"credits_used":{"type":"number","description":"The number of tokens consumed during generation."},"usd_spent":{"type":"number","description":"The total amount of money spent by the user in USD."}},"required":["credits_used","usd_spent"]}},"description":"Additional details about the generation."}},"required":["audio"]}},"audio/wav":{"schema":{"type":"string","format":"binary","description":"Audio stream"}}}}}}}}}
```

## Code Example

{% tabs %}
{% tab title="Python" %}
{% code overflow="wrap" %}

```python
import os
import requests

def main():
    url = "https://api.aimlapi.com/v1/tts"
    headers = {
        # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
        "Authorization": "Bearer <YOUR_AIMLAPI_KEY>",
    }
    payload = {
        "model": "minimax/speech-2.5-turbo-preview",
        "text": "Hi! What are you doing today?",
        "voice_setting": {
          "voice_id": "Wise_Woman"
        }
    }

    response = requests.post(url, headers=headers, json=payload, stream=True)
    dist = os.path.abspath("your_file_name.wav")

    with open(dist, "wb") as write_stream:
        for chunk in response.iter_content(chunk_size=8192):
            if chunk:
                write_stream.write(chunk)

    print("Audio saved to:", dist)

main()
```

{% endcode %}
{% endtab %}

{% tab title="JavaScript" %}
{% code overflow="wrap" %}

```javascript
import fs from "fs";
import path from "path";

async function main() {
  const url = "https://api.aimlapi.com/v1/tts";
  const payload = {
    model: "minimax/speech-2.5-hd-preview",
    text: "Hi! What are you doing today?",
    voice_setting: {
      voice_id: "Wise_Woman"
    }
  };

  const response = await fetch(url, {
    method: "POST",
    headers: {
      // Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
      "Authorization": `Bearer <YOUR_AIMLAPI_KEY>`,
      "Content-Type": "application/json"
    },
    body: JSON.stringify(payload)
  });

  // Read response as ArrayBuffer and convert to Buffer
  const arrayBuffer = await response.arrayBuffer();
  const buffer = Buffer.from(arrayBuffer);

  // Save audio to file in the current working directory
  const dist = path.join(process.cwd(), "your_file_name.wav");
  fs.writeFileSync(dist, buffer);

  console.log("Audio saved to:", dist);
}

main();
```

{% endcode %}
{% endtab %}
{% endtabs %}

<details>

<summary>Response</summary>

{% code overflow="wrap" %}

```
Audio saved to: c:\Users\user\Documents\Python Scripts\TTSes\your_file_name.wav
```

{% endcode %}

</details>

{% embed url="<https://drive.google.com/file/d/1y1mFt6P-PTHRUW2Rzxkc2TRXR27XP9Gd/view?usp=sharing>" %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.aimlapi.com/api-references/speech-models/voice-chat/minimax/speech-2.5-hd-preview.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.