مرجع CLI

speech transcribe <file> [options]

# Basic transcription
speech transcribe recording.wav

# Use larger model
speech transcribe recording.wav --model 1.7B

# CoreML encoder (Neural Engine + MLX decoder)
speech transcribe recording.wav --engine qwen3-coreml

# Use Parakeet (CoreML) engine
speech transcribe recording.wav --engine parakeet

# Use Nemotron Streaming (CoreML, English with native punctuation)
speech transcribe recording.wav --engine nemotron                                 # batch
speech transcribe recording.wav --engine nemotron --stream --partial              # streaming

# Omnilingual (CoreML, 1,672 languages)
speech transcribe recording.wav --engine omnilingual                              # 10 s window
speech transcribe recording.wav --engine omnilingual --window 5                     # 5 s window

# Omnilingual (MLX, any length up to 40 s)
speech transcribe recording.wav --engine omnilingual --backend mlx                              # 300M @ 4-bit
speech transcribe recording.wav --engine omnilingual --backend mlx --variant 1B                  # 1B @ 4-bit
speech transcribe recording.wav --engine omnilingual --backend mlx --variant 3B --bits 8         # 3B @ 8-bit
speech transcribe recording.wav --engine omnilingual --backend mlx --variant 7B                  # 7B @ 4-bit

# Streaming with VAD
speech transcribe recording.wav --stream --partial

speech align <file> [options]

# Auto-transcribe then align
speech align recording.wav

# Align with known text
speech align recording.wav --text "Can you guarantee that the replacement part will be shipped tomorrow?"

speech speak "<text>" [options]

# Basic TTS
speech speak "Hello, world!" --output hello.wav

# Voice cloning (Qwen3-TTS)
speech speak "Hello in your voice" --voice-sample reference.wav -o cloned.wav

# Voice cloning (CosyVoice)
speech speak "Hello in your voice" --engine cosyvoice --voice-sample reference.wav -o cloned.wav

# CosyVoice multilingual
speech speak "Hallo Welt" --engine cosyvoice --language german -o hallo.wav

# Multi-speaker dialogue
speech speak "[S1] Hello there! [S2] Hey, how are you?" \
    --engine cosyvoice --speakers s1=alice.wav,s2=bob.wav -o dialogue.wav

# Inline emotion/style tags
speech speak "(excited) Wow, amazing! (sad) But I have to go..." \
    --engine cosyvoice -o emotion.wav

# Combined: dialogue + emotions + voice cloning
speech speak "[S1] (happy) Great news! [S2] (surprised) Really?" \
    --engine cosyvoice --speakers s1=alice.wav,s2=bob.wav -o combined.wav

# Custom style instruction
speech speak "Hello world" --engine cosyvoice --cosy-instruct "Speak cheerfully" -o cheerful.wav

# Magpie multilingual TTS — same Aria voice across 9 languages
speech speak "Hello, world." --engine magpie --magpie-speaker aria \
    --magpie-temperature 0 -o en.wav
speech speak "Hola mundo." --engine magpie --language es --magpie-speaker aria \
    --magpie-temperature 0 -o es.wav
# Japanese needs stochastic sampling
speech speak "こんにちは世界、これは音声合成システムです。" \
    --engine magpie --language ja --magpie-temperature 0.6 \
    --magpie-top-k 80 --seed 42 -o ja.wav
speech speak --engine magpie --list-speakers

# Magpie CoreML backend (ANE-accelerated, 8 languages, no streaming)
speech speak "Hello world." --engine magpie-coreml --magpie-speaker aria -o en.wav
speech speak "Hola mundo." --engine magpie-coreml --language es \
    --magpie-speaker leo -o es.wav
# Japanese auto-routes to MLX (CoreML bundle has no JA tokenizer)
speech speak "こんにちは。" --engine magpie-coreml --language ja -o ja.wav

# Streaming synthesis
speech speak "Long text here..." --stream

# Batch synthesis from file
speech speak --batch-file texts.txt --batch-size 4

# VoxCPM2 — 48 kHz studio output
speech speak "Hello there." --engine voxcpm2 --voxcpm2-variant int8 -o hi.wav

# VoxCPM2 — voice design
speech speak "Welcome to the show." --engine voxcpm2 \
    --voxcpm2-instruct "A young woman, warm and gentle voice." -o design.wav

# VoxCPM2 — single-reference cloning
speech speak "This is a cloned voice." --engine voxcpm2 \
    --voice-sample speaker.wav -o clone.wav

speech kokoro "<text>" [options]

# Basic Kokoro TTS
speech kokoro "Hello, world!" --voice af_heart -o hello.wav

# French voice
speech kokoro "Bonjour le monde" --voice ff_siwis --language fr -o bonjour.wav

# List all 50 voices
speech kokoro --list-voices

speech respond [options]

# Basic speech-to-speech
speech respond --input question.wav

# Use a female voice with compiled transformer
speech respond -i question.wav --voice NATF1 --compile

# Stream response and show transcript
speech respond -i question.wav --stream --transcript --verbose

speech vad <file> [options]

speech vad-stream <file> [options]

speech wake <file> [options]

# Plain phrase, tuned defaults
speech wake recording.wav --keywords "hey soniqo"

# Explicit BPE pieces for phrases the greedy tokenizer gets wrong
speech wake recording.wav --keywords "LIGHT UP|▁ L IGHT ▁UP:0.25:2.0"

# Multiple phrases + JSON output
speech wake recording.wav \
  --keywords "lovely child|▁LOVE LY ▁CHI L D:0.25:2.0" \
             "for ever|▁FOR E VER:0.25:2.0" \
  --json

speech diarize <file> [options]

# Basic diarization (pyannote, default)
speech diarize meeting.wav

# End-to-end Sortformer (CoreML, Neural Engine)
speech diarize meeting.wav --engine sortformer

# RTTM output for evaluation
speech diarize meeting.wav --rttm

# Target speaker extraction (pyannote only)
speech diarize meeting.wav --target-speaker enrollment.wav

# Score against reference
speech diarize meeting.wav --score-against reference.rttm

speech embed-speaker <file> [options]

speech denoise <file> [options]

speech denoise noisy-recording.wav -o clean.wav

speech compose <prompt> [options]

# Default: small-int4, ~10 s wall on M-series for a 30 s clip
speech compose "happy rock" -o happy_rock.wav

# Larger model — better prompt following, slower
speech compose "lo-fi hip hop with mellow piano" --variant medium-int4 -o lofi.wav

# Reproducible
speech compose "energetic EDM with synth lead" --seed 42 -o edm.wav