This version is still in development and is not considered stable yet. For the latest stable version, please use dengjen 3.x!

Synthesizing speech

Dengjen synthesizes speech from a Piper voice. Download a voice’s .onnx model and matching .onnx.json config from the Piper voices repository and keep both files together, e.g. voices/en_US-lessac-medium.onnx and voices/en_US-lessac-medium.onnx.json.

A voice doesn’t have to come from the official Piper voices repository — any VITS-family ONNX export using the same 3/4-input tensor convention (phoneme ids, lengths, scales, optional speaker id) can be loaded by writing a matching .onnx.json manifest with "model_type": "vits". The minimal required fields are audio (sample rate), inference (noise_scale/length_scale/noise_w), and phoneme_id_map (the symbol vocabulary); phoneme_type selects the phonemizer (espeak is the default if omitted, and needs an espeak.voice entry — text, hebrew, and pinyin don’t).

A MeloTTS voice — its own VITS-derived ONNX export, with a tones tensor alongside phone ids — is loaded with "model_type": "melotts". The required fields are audio (sample rate), inference (noise_scale/length_scale/noise_scale_w), phone_id_map and tone_id_map (the phone and tone symbol vocabularies), and model_path; phonemizer selects the phonemization backend and must be one of {"type": "espeak", "voice": "<espeak-ng voice name>"} (covers English, Spanish, French, Japanese, Korean) or {"type": "pinyin", "model_dir": "<g2pW model directory>"} (Chinese, with real tone extraction — requires building with the pinyin feature).

CLI

Synthesize text from a file to a WAV file, using the dengjen CLI (crate dengjen-tts-cli). The speak argument is a model config path or the key of an installed voice (see Managing voices).

Synthesis moved to the speak subcommand. dengjen <config> no longer works; use dengjen speak <config>. 
cargo run --release -p dengjen-tts-cli -- speak voices/en_US-lessac-medium.onnx.json \
    -f input.txt \
    -o output.wav

Or send a single request as JSON on stdin and capture the WAV bytes written to stdout:

echo '{"text": "Hello world"}' | cargo run --release -p dengjen-tts-cli -- speak voices/en_US-lessac-medium.onnx.json > output.wav

Run dengjen speak --help (or cargo run --release -p dengjen-tts-cli — speak --help) for the full list of options. The main ones:

  • --mode lazy|parallel|batched|realtime selects the synthesis mode (default lazy). --batch-size sets how many sentences batched synthesizes per concurrent group, and --chunk-size and --chunk-padding tune realtime chunking.

  • --speaker-id picks a speaker for multi-speaker voices; when omitted, the voice’s own default speaker from its manifest is used (Kokoro’s is 0).

  • --rate, --pitch and --volume take 0-100. When omitted, each stays at 1.0 (no change). The value maps linearly onto a speed of 0.5x-5.5x (so 10 is 1x and 50 is 3x), a pitch of 0.5-1.5 and a volume gain of 0-1 (a volume of 0 mutes the audio). --silence appends that many milliseconds of silence after each sentence; --rate also changes how long that silence lasts, because the silence is processed like the rest of the audio.

  • --length-scale, --noise-scale and --noise-w override inference knobs: --noise-w is Piper’s, while --length-scale and --noise-scale also apply to MeloTTS. --param KEY=VALUE (repeatable) sets a named backend parameter to a number, such as MeloTTS’s noise_scale_w (an unrecognized key may be silently ignored); a named flag wins over a conflicting --param.

Managing voices

dengjen voices lists, installs and removes Piper voices from the catalogue. Voices live in ~/.local/share/dengjen/voices (the platform data directory elsewhere).

dengjen voices                        # same as `dengjen voices list`
dengjen voices list --lang ku --json  # JSON array on stdout
dengjen voices list --installed       # works offline
dengjen voices install ku_TR-berfin_renas-medium
dengjen speak ku_TR-berfin_renas-medium -f input.txt -o output.wav
dengjen voices remove ku_TR-berfin_renas-medium
dengjen voices refresh                # re-download the catalogue, print the voice count

Results go to stdout, with installed voices marked (installed in the table, "installed": true in JSON); progress and errors go to stderr. Exit codes: 0 success, 1 error, 2 another install or removal of the same voice is running. Override the locations with --voices-dir, --catalogue-url and --files-base-url (accepted before or after the subcommand; speak also takes --voices-dir), or the DENGJEN_VOICES_DIR, DENGJEN_CATALOGUE_URL and DENGJEN_FILES_BASE_URL environment variables. Ctrl-C stops an install; running it again resumes the download.