Synthesize text to speech. Supports WAV and MP3 formats. The format is automatically selected based on the model: mistv2 and mist output MP3 while arcana and arcanav2 default to WAV but support MP3 as well. Use --format to override.
rime tts TEXT --speaker VOICE --model-id MODEL
Required flags
| Flag | Short | Description |
|---|
--speaker | -s | Voice speaker to use (e.g., astra, celeste, orion) |
--model-id | -m | Model ID: arcana, arcanav2, mistv2, or mist |
Optional flags
| Flag | Short | Default | Description |
|---|
--output | -o | — | Output file path. Use - for stdout. If omitted, plays audio directly |
--play | -p | false | Play audio after synthesis (default behavior when no output is specified) |
--lang | -l | eng | Language code (e.g., eng, es, fra). Valid codes depend on model |
--format | -f | — | Audio format: wav or mp3 (overrides model default) |
--speed-alpha | — | 1 | Speed multiplier — must be greater than 0 |
--sampling-rate | — | — | Output sampling rate in Hz. Arcana: 8000, 16000, 22050, 24000, 44100, 48000, 96000. Mist: 4000–44100 |
--api-url | — | — | API URL (default: $RIME_API_URL or https://users.rime.ai/v1/rime-tts) |
Arcana/arcanav2 flags
| Flag | Default | Description |
|---|
--temperature | 0.5 | Sampling temperature (0–1) |
--top-p | 1 | Top-p nucleus sampling (0–1) |
--max-tokens | 1200 | Max output tokens (200–5000) |
--repetition-penalty | 1.5 | Repetition penalty (1–2) |
Mist/mistv2 flags
| Flag | Description |
|---|
--no-text-normalization | Disable text normalization |
--pause-between-brackets | Insert pause at bracketed markers |
--phonemize-between-brackets | Phonemize text in brackets |
--inline-speed-alpha | Comma-separated per-segment speed values |
--save-oovs | Save out-of-vocabulary words |
Examples
# Play audio directly through speakers
rime tts "Hello world" -s astra -m arcana
# Save to a WAV file
rime tts "Hello world" -s astra -m arcana -o output.wav
# Pipe audio to stdout
rime tts "Hello world" -s astra -m arcana -o - > audio.wav
# Use mistv2 (requires MP3 format)
rime tts "Hello world" -s peak -m mistv2 -f mp3
# Synthesize in Spanish with Arcana
rime tts "Hola mundo" -s astra -m arcana -l es
# JSON output with timing metadata
rime tts "Hello world" -s astra -m arcana -o output.wav --json
Supported languages by model
| Model | Languages |
|---|
arcana | eng, ara, fra, ger, heb, hin, jpn, por, sin, spa, tam (and ISO 639-1 equivalents) |
arcanav2 | eng, spa, ger, fra, hin (and ISO 639-1 equivalents) |
mistv2 / mist | eng, fra, ger, spa (and ISO 639-1 equivalents) |
The mist and mistv2 models require --format mp3. The CLI returns an error if you omit it.
