whisper.cpp/examples/talk-llama/speak

#!/bin/bash

# Usage:
#  speak.sh <voice_id> <text-to-speak>

# espeak
# Mac OS: brew install espeak
# Linux: apt-get install espeak
#
#espeak -v en-us+m$1 -s 225 -p 50 -a 200 -g 5 -k 5 "$2"

# piper
#
# https://github.com/rhasspy/piper
#
# Tested with Linux:
#
#echo "$2" | piper --model ~/en_US-lessac-medium.onnx --output-raw | aplay -q -r 22050 -f S16_LE -t raw -

# for Mac
say "$2"

# Eleven Labs
# To use it, install the elevenlabs module from pip (pip install elevenlabs)
# It's possible to use the API for free with limited number of characters. To increase this limit register to https://beta.elevenlabs.io to get an api key and paste it after 'ELEVEN_API_KEY='
#Keep the line commented to use the free version whitout api key
#
#export ELEVEN_API_KEY=your_api_key
#wd=$(dirname $0)
#script=$wd/eleven-labs.py
#python3 $script $1 "$2" >/dev/null 2>&1
#ffplay -autoexit -nodisp -loglevel quiet -hide_banner -i ./audio.mp3 >/dev/null 2>&1
talk-llama : add new example + sync ggml from llama.cpp (#664) * talk-llama : talk with LLaMA AI * talk.llama : disable EOS token * talk-llama : add README instructions * ggml : fix build in debug 2023-03-27 18:00:32 +00:00			`#!/bin/bash`

			`# Usage:`
			`# speak.sh <voice_id> <text-to-speak>`

			`# espeak`
			`# Mac OS: brew install espeak`
			`# Linux: apt-get install espeak`
			`#`
			`#espeak -v en-us+m$1 -s 225 -p 50 -a 200 -g 5 -k 5 "$2"`

talk-llama : add optional Piper TTS support (#1749) Add commented-out command to optionally use Piper (https://github.com/rhasspy/piper) as text-to-speech solution for the talk-llama example. Piper voices sound almost like real people which is a big improvement (e.g.) from something like espeak. 2024-01-10 14:15:28 +00:00			`# piper`
			`#`
			`# https://github.com/rhasspy/piper`
			`#`
			`# Tested with Linux:`
			`#`
			`#echo "$2" \| piper --model ~/en_US-lessac-medium.onnx --output-raw \| aplay -q -r 22050 -f S16_LE -t raw -`

talk-llama : add new example + sync ggml from llama.cpp (#664) * talk-llama : talk with LLaMA AI * talk.llama : disable EOS token * talk-llama : add README instructions * ggml : fix build in debug 2023-03-27 18:00:32 +00:00			`# for Mac`
			`say "$2"`

			`# Eleven Labs`
examples : update elevenlabs scripts to use official python API (#837) * Update elevenlabs example to use ufficial python API * Update elevenlabs example to use official python API 2023-05-24 18:11:01 +00:00			`# To use it, install the elevenlabs module from pip (pip install elevenlabs)`
			`# It's possible to use the API for free with limited number of characters. To increase this limit register to https://beta.elevenlabs.io to get an api key and paste it after 'ELEVEN_API_KEY='`
			`#Keep the line commented to use the free version whitout api key`
talk-llama : add new example + sync ggml from llama.cpp (#664) * talk-llama : talk with LLaMA AI * talk.llama : disable EOS token * talk-llama : add README instructions * ggml : fix build in debug 2023-03-27 18:00:32 +00:00			`#`
examples : update elevenlabs scripts to use official python API (#837) * Update elevenlabs example to use ufficial python API * Update elevenlabs example to use official python API 2023-05-24 18:11:01 +00:00			`#export ELEVEN_API_KEY=your_api_key`
talk-llama : add new example + sync ggml from llama.cpp (#664) * talk-llama : talk with LLaMA AI * talk.llama : disable EOS token * talk-llama : add README instructions * ggml : fix build in debug 2023-03-27 18:00:32 +00:00			`#wd=$(dirname $0)`
			`#script=$wd/eleven-labs.py`
			`#python3 $script $1 "$2" >/dev/null 2>&1`
			`#ffplay -autoexit -nodisp -loglevel quiet -hide_banner -i ./audio.mp3 >/dev/null 2>&1`