VoiSona Talk API

Appearance

CLI Usage ​

VoiSona Talk API library includes a built-in CLI tool that allows you to interact with the API directly from your terminal.

Installation ​

The CLI is included in the voisona-talk-api package. You can use it via npx without installation, or install it globally.

bash
# Via npx
npx voisona status

# Global installation
pnpm add -g voisona-talk-api
voisona status

Commands ​

status ​

Check if the VoiSona Talk API service is running and reachable.

bash
voisona status

list voices ​

List all available voice libraries installed in your VoiSona Talk editor.

bash
voisona list voices

voices info <name> ​

Get detailed information about a specific voice, including its available styles and supported languages.

bash
voisona voices info "Chis-A"

synthesis request <text> ​

Synthesize text to speech and save it as a WAV file.

bash
# 基本的な使い方
voisona synthesis request "こんにちは"

# 特定のボイスと出力パスを指定する場合
voisona synthesis request "こんにちは、世界！" --voice_name "Chis-A" --output "./hello.wav"

Advanced synthesis options ​

The synthesis request command supports additional voice tuning and pronunciation control.

  • --speed <value>: Speech speed multiplier (0.2-5).
  • --pitch <value>: Pitch shift in cents (-600 to 600).
  • --intonation <value>: Pitch contour intensity (0-2).
  • --volume <value>: Volume offset in dB (-8 to 8).
  • --huskiness <value>: Huskiness control (-20 to 20).
  • --alp <value>: Age-like voice parameter (-1 to 1).
  • --styles <list>: Style weight map for emotion control. Example: Happy:0.8,Angry:0.2.
  • --pron <list>: Pronunciation corrections for specific words. Example: 焦る:アセル.
  • --params <json>: Raw JSON request parameters to merge with the synthesis request.

--styles is best used with --voice_name so the CLI can resolve style names to the voice's style index order.

bash
voisona synthesis request "本当に嬉しいです" --voice_name "小春六花" --styles "Happy:0.8,Angry:0.2"
voisona synthesis request "焦る必要はありません。" --voice_name "小春六花" --pron "焦る:アセル"
voisona synthesis request "これはテストです" --voice_name "小春六花" --params '{"can_overwrite_file": true}'

Global Options ​

The following options are available for all commands:

  • --email <email>: API user email (can also be set via VOISONA_EMAIL env var).
  • --password <pass>: API user password (can also be set via VOISONA_PASSWORD env var).
  • --baseUrl <url>: Base URL of the API (default: http://localhost:32766/api/talk/v1).
  • --env-file <path>: Path to a .env file containing credentials.
  • --json: Output result in JSON format.
  • --verbose, -v: Enable verbose logging (shows selected voice and text being synthesized).
  • -h, --help: Show help message.

JSON Output ​

Use the --json flag to get machine-readable output. This is useful for integration with other tools or scripts.

bash
voisona list voices --json

Examples ​

Using with a .env file ​

bash
voisona synthesize "Testing" --env-file .env.production

Getting specific voice styles via JSON ​

bash
voisona voices info "Chis-A" --json