Coze Text-to-Speech (TTS)

Convert text to natural-sounding speech using Coze API.

Setup

1. Get your API Key:
Get a key from Coze Platform

2. Set it in your environment:
CODEBLOCK0

Supported Output Formats

• - MP3 - Default format, widely compatible
• OGG_OPUS - Optimized for streaming and messaging
• WAV - Uncompressed audio
• PCM - Raw audio data

Usage

Basic TTS

Convert text to speech with default settings:

CODEBLOCK1

Save to Specific File

CODEBLOCK2

Use Different Voice

CODEBLOCK3

Change Output Format

CODEBLOCK4

Full Options

CODEBLOCK5

Parameters:

• - text (required): Text to convert to speech
• INLINECODE1 (optional): Output file path (default: auto-generated)
• INLINECODE2 (optional): Voice ID (default: 1)
• INLINECODE3 (optional): Output format - mp3/ogg_opus/wav/pcm (default: mp3)

Output

The script saves the audio file and outputs:

• - File path
• File size
• Audio duration (if ffprobe is available)

Example output:
CODEBLOCK6

Workflow Examples

Generate Notification Audio

CODEBLOCK7

Create Voice Greeting

CODEBLOCK8

Generate OGG for Messaging

CODEBLOCK9

Batch Generate

CODEBLOCK10

Integration with Other Skills

Combine with coze-asr for voice conversation:

CODEBLOCK11

Troubleshooting

Authentication Error:

• - Check COZEAPIKEY is set correctly
• Verify API key has TTS permissions

Invalid Voice ID:

• - Voice ID should be a number (int64 format)
• Try voice_id: 1 as default

File Not Created:

• - Check write permissions in output directory
• Ensure sufficient disk space

Limitations

• - Text length limits apply (check Coze documentation)
• Rate limits may apply based on your plan
• Some voices may not support all output formats

API Reference

• - Endpoint: INLINECODE5
• Authentication: Bearer token (COZEAPIKEY)
• Content-Type: application/json

Required Environment Variables

Required Tools

License

MIT