Cheap TTS CLI

Generate multilingual WAV audio from a terminal, shell script, or CI job. The CLI uses the Cheap TTS Node SDK, performs inference locally, and reuses the same model cache between runs.

An active Cheap TTS subscription, Node.js 20+, and a secret server key are required.

npm install --global @cheap-tts/cli
export CHEAP_TTS_SECRET_KEY="sk_live_your_project"

cheap-tts synthesize "Xin chào từ Cheap TTS." \
  --voice vi-entertainment \
  --output speech.wav

Pipe text or read a UTF-8 file:

echo "Hello from Cheap TTS." | cheap-tts say --voice en-narration --output hello.wav
cheap-tts synthesize --file script.txt --voice vi-commentary --output narration.wav

Discover voice IDs and manage the local model cache:

cheap-tts voices
cheap-tts voices --json
cheap-tts cache clear

Use --json for automation. JSON and audio output are written to stdout; progress and errors are written to stderr. Pass --output - to stream WAV bytes to stdout.

The CLI sends operational health telemetry (success/failure stage, latency, character count, voice ID, and audio duration). It never sends TTS text or credentials. Pass --no-telemetry to disable it.

• Full CLI documentation
• Dashboard

Reading pauses

Pauses are left to the voice model by default. Add a flag to insert real silence after a punctuation mark instead, in seconds (0-2):

cheap-tts say "Xin chào." \
  --pause-sentence 0.4 \
  --pause-comma 0.2 \
  --pause-paragraph 0.8

Omit the flags to keep the audio you get today. Raising a value costs generation speed, because the audio has to be cut at that boundary for silence to follow it.