MirrorMirror
/
01
mirror of https://github.com/OpenInterpreter/01.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

quick hack to support audio/raw in tts

This commit is contained in:
Theia Vogel 2024-02-18 01:31:16 -08:00
parent 801a049b77
commit 5348f569b0
1 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
01OS/01OS/server/tts/tts.py
View File

@ -6,6 +6,7 @@ from pydub import AudioSegment
from dotenv import load_dotenv from dotenv import load_dotenv
load_dotenv() # take environment variables from .env. load_dotenv() # take environment variables from .env.
import ffmpeg
import tempfile import tempfile
from openai import OpenAI from openai import OpenAI
import os import os
@ -28,11 +29,17 @@ def stream_tts(text):
input=text, input=text,
response_format="opus" response_format="opus"
) )
with tempfile.NamedTemporaryFile(suffix=".opus") as temp_file: with tempfile.NamedTemporaryFile(suffix=".opus", delete=False) as temp_file:
response.stream_to_file(temp_file.name) response.stream_to_file(temp_file.name)
audio_bytes = temp_file.read() # TODO: hack to format audio correctly for device
file_type = "bytes.opus" outfile = tempfile.gettempdir() + "/" + "raw.dat"
ffmpeg.input(temp_file.name).output(outfile, f="s16le", ar="16000", ac="1").run()
with open(outfile, "rb") as f:
audio_bytes = f.read()
file_type = "bytes.raw"
print(outfile, len(audio_bytes))
os.remove(outfile)
else: else:
with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as temp_file: with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as temp_file: