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

# GLM Text to Speech

Use GLM-TTS to convert text into natural speech, with support for multiple voices, emotion control, and intonation adjustment.

## Request Headers

<ParamField header="Content-Type" type="string" required={true}>
  Enum: `application/json`
</ParamField>

<ParamField header="Authorization" type="string" required={true}>
  Bearer authentication format: Bearer \{\{API Key}}.
</ParamField>

## Request Body

<ParamField body="input" type="string" required={true}>
  Text to be converted to speech.

  Length limit: 0 - 1024
</ParamField>

<ParamField body="speed" type="number" default={1}>
  Speech rate. Default is 1.0. Range: \[0.5, 2].

  Range: \[0.5, 2]
</ParamField>

<ParamField body="voice" type="string" required={true} default="tongtong">
  Voice timbre used for audio generation. Supports both system voices and cloned voices. System voices include: tongtong (default), chuichui, xiaochen, jam, kazi, douji, luodo.
</ParamField>

<ParamField body="volume" type="number" default={1}>
  Volume. Default is 1.0. Range: (0, 10].

  Range: \[0, 10]
</ParamField>

<ParamField body="response_format" type="string" default="pcm">
  Audio output format. Defaults to pcm format.

  Possible values: `wav`, `pcm`
</ParamField>

<ParamField body="watermark_enabled" type="boolean">
  Controls whether a watermark is added to AI-generated audio. true: enables explicit and implicit digital watermarks by default, compliant with policy requirements. false: disables all watermarks, only effective for users who have completed the watermark removal process.
</ParamField>

## Response

On success, the recommended sample rate is 24000.

Format: `binary`