rime tts

Synthesize text to speech from the command line using the Rime CLI.

Synthesize text to speech in WAV or MP3. The CLI picks the format from the model: mist and mistv2 output MP3, while coda and mistv3 default to WAV. Deprecated Arcana identifiers also default to WAV. 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. Use coda, mistv3, mistv2, or mist. arcana and arcanav2 remain available only for deprecated integrations.

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. For mist/mistv2: lower is faster. For coda, mistv3, and deprecated Arcana identifiers: higher is faster
--sampling-rate	—	—	Output sampling rate in Hz. Coda and deprecated Arcana identifiers: 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)

Deprecated Arcana compatibility flags

These flags remain for existing Arcana integrations. Do not use Arcana for new requests.

Flag	Default	Description
--max-tokens	1200	Max output tokens (200–5000)

mist/mistv2/mistv3 flags

Flag	Description
--inline-time-scale-factor	Comma-separated per-segment speed values
--pause-between-brackets	Insert pause at bracketed markers

mist/mistv2 flags

Only mist and mistv2 support these flags; mistv3 does not.

Flag	Description
--phonemize-between-brackets	Phonemize text in brackets (see Custom pronunciation)
--no-text-normalization	Disable text normalization

Examples

# Play audio directly through speakers
rime tts "Hello world" -s astra -m coda

# Save to a WAV file
rime tts "Hello world" -s astra -m coda -o output.wav

# Pipe audio to stdout
rime tts "Hello world" -s astra -m coda -o - > audio.wav

# Use mistv3 (WAV by default)
rime tts "Hello world" -s peak -m mistv3

# Use mistv2 (outputs MP3 by default)
rime tts "Hello world" -s peak -m mistv2

# Synthesize in Spanish with Coda
rime tts "Hola mundo" -s astra -m coda -l es

# JSON output with timing metadata
rime tts "Hello world" -s astra -m coda -o output.wav --json

Supported languages by model

Model	Languages
coda	eng, spa, fra, por, ger, jpn (and ISO 639-1 equivalents)
mistv3	eng, fra, ger, spa (and ISO 639-1 equivalents)
mistv2 / mist	eng, fra, ger, spa (and ISO 639-1 equivalents)
arcana (deprecated)	eng, spa, fra, por, ger, jpn, tam, sin, heb (and ISO 639-1 equivalents)
arcanav2 (deprecated)	eng, spa, ger, fra (and ISO 639-1 equivalents)

The mist and mistv2 models default to MP3. coda, mistv3, and the deprecated Arcana identifiers default to WAV. Use --format to override.