> ## Documentation Index
> Fetch the complete documentation index at: https://docs.profy.cn/llms.txt
> Use this file to discover all available pages before exploring further.

# Voice Synthesis & Recognition

> Text-to-Speech (TTS) and Speech-to-Text (ASR)

Profy Expert provides two voice capabilities: **Text-to-Speech (TTS)** that converts text into natural-sounding human voice, and **Automatic Speech Recognition (ASR)** that transcribes audio files into text.

## Two Core Capabilities

<CardGroup cols={2}>
  <Card title="Text-to-Speech (TTS)" icon="volume-high">
    Convert text content into natural, fluent speech audio. Supports multiple voice styles, ideal for audio content creation.
  </Card>

  <Card title="Speech Recognition (ASR)" icon="microphone">
    Transcribe speech from audio files into text. Supports long audio, ideal for meeting notes and content organization.
  </Card>
</CardGroup>

***

## Text-to-Speech (TTS)

### How to Use

Tell Expert in the conversation which content you'd like converted to speech:

* "Read this article aloud"
* "Record an opening statement for me in a soft female voice"
* "Convert the following text to speech: ..."

Expert will convert the specified text into an audio file that you can listen to and download directly in the conversation.

### Voice Selection

You can specify your preferred voice type in your request. Different models offer different voice options, typically including:

* Male / Female
* Young / Mature
* Gentle / Powerful
* News broadcast / Casual conversation

<Tip>
  Not sure which voice to pick? Have Expert read a sample sentence in different voices, then choose your favorite before generating the full content.
</Tip>

### Use Cases

<AccordionGroup>
  <Accordion title="Audiobooks">
    Convert written manuscripts into audio content — quickly produce sample clips for audiobooks or audio courses.
  </Accordion>

  <Accordion title="Video Voiceover">
    Generate narration voiceovers for video content, pairing with the video generation capability.
  </Accordion>

  <Accordion title="Accessibility">
    Convert documents and web content into speech for visually impaired users or for consuming information on the go.
  </Accordion>

  <Accordion title="Content Repurposing">
    Quickly convert written content into audio format for publishing on podcast or audio platforms.
  </Accordion>
</AccordionGroup>

***

## Speech Recognition (ASR)

### How to Use

<Steps>
  <Step title="Upload an Audio File">
    Drag and drop the audio file you want to transcribe (e.g., MP3, WAV, M4A) into the chat, or click the attachment button to upload.
  </Step>

  <Step title="Request Transcription">
    Tell Expert what you need, such as "transcribe this recording into text" or "extract the key points from this meeting recording."
  </Step>

  <Step title="Get the Results">
    Expert will return the transcribed text content. You can then ask Expert to format the text, extract summaries, or translate it into other languages.
  </Step>
</Steps>

### Use Cases

<AccordionGroup>
  <Accordion title="Meeting Minutes">
    Upload meeting recordings and have Expert transcribe and organize structured meeting minutes, including topics, decisions, and action items.
  </Accordion>

  <Accordion title="Interview Transcription">
    Convert interview recordings into text transcripts. Expert can also help distinguish between different speakers.
  </Accordion>

  <Accordion title="Study Notes">
    After transcribing recordings, have Expert extract key points, generate mind maps, or organize study notes.
  </Accordion>

  <Accordion title="Multilingual Processing">
    After transcription, you can directly have Expert translate the content — enabling a "listen in one language, read in another" workflow.
  </Accordion>
</AccordionGroup>

<Tip>
  After transcription is complete, you can directly ask Expert to further process the text — summarize key points, extract critical information, generate action item lists, and more — without switching tools.
</Tip>

***

## Usage Tips

<Warning>
  * Audio quality directly affects recognition accuracy. Use clear recordings with minimal background noise whenever possible
  * Very noisy environment recordings may result in transcription gaps or errors
  * Technical jargon or uncommon proper nouns may require manual correction after transcription
</Warning>

## Billing

| Capability               | Billing Method        | Notes                                                                                  |
| ------------------------ | --------------------- | -------------------------------------------------------------------------------------- |
| Text-to-Speech (TTS)     | Per 10,000 characters | Cost scales with text length; CJK and English characters have different counting rules |
| Speech Recognition (ASR) | By audio duration     | Cost is proportional to the number of audio seconds                                    |

Specific rates depend on the selected model — refer to the real-time pricing shown in the product.