mirror of
https://github.com/xinnan-tech/xiaozhi-esp32-server.git
synced 2026-07-28 01:53:53 +08:00
Merge branch 'py_test_error_response' into fix/2075
This commit is contained in:
@@ -89,7 +89,8 @@ xiaozhi:
|
||||
transport: websocket
|
||||
audio_params:
|
||||
format: opus
|
||||
sample_rate: 16000
|
||||
# Opus支持的采样率范围为[8000, 12000, 16000, 24000, 48000]
|
||||
sample_rate: 24000
|
||||
channels: 1
|
||||
frame_duration: 60
|
||||
|
||||
@@ -717,13 +718,31 @@ TTS:
|
||||
speaker: zh_female_wanwanxiaohe_moon_bigtts
|
||||
# 开启WebSocket连接复用,默认复用(注意:复用后设备处于聆听状态时空闲链接会占并发数)
|
||||
enable_ws_reuse: True
|
||||
speech_rate: 0
|
||||
loudness_rate: 0
|
||||
pitch: 0
|
||||
# 多情感音色参数,注意:当前仅部分音色支持设置情感。
|
||||
# 相关音色列表:https://www.volcengine.com/docs/6561/1257544
|
||||
emotion: "neutral" # 情感类型,可选值为:neutral、happy、sad、angry、fearful、disgusted、surprised
|
||||
emotion_scale: 4 # 情感强度,可选值为:1~5,默认值为4
|
||||
# 相关参数文档:https://www.volcengine.com/docs/6561/1329505
|
||||
# 音频输出配置(audio_params)- 用户可自定义添加火山引擎支持的任何音频参数
|
||||
audio_params:
|
||||
speech_rate: 0 # 语速(-50~100)
|
||||
loudness_rate: 0 # 音量(-50~100)
|
||||
# 多情感音色参数,注意:当前仅部分音色支持设置情感。
|
||||
# 相关音色列表:https://www.volcengine.com/docs/6561/1257544
|
||||
# emotion: "neutral" # 情感类型(仅部分音色支持):neutral、happy、sad、angry、fearful、disgusted、surprised
|
||||
# emotion_scale: 4 # 情感强度(1~5)
|
||||
# 高级文本处理配置(additions)- 用户可自定义添加火山引擎支持的任何高级参数
|
||||
additions:
|
||||
post_process:
|
||||
pitch: 0 # 音高(-12~12)
|
||||
# aigc_metadata: {} # AIGC元数据配置
|
||||
# cache_config: {} # 缓存配置
|
||||
# 混音控制配置(mix_speaker)- 多音色混合(仅 TTS 1.0)
|
||||
# 混音功能主要适用于豆包语音合成模型1.0的音色,使用时需要将req_params.speaker设置为custom_mix_bigtts
|
||||
# mix_speaker:
|
||||
# speakers:
|
||||
# - source_speaker: zh_male_bvlazysheep
|
||||
# mix_factor: 0.3
|
||||
# - source_speaker: BV120_streaming
|
||||
# mix_factor: 0.3
|
||||
# - source_speaker: zh_male_ahu_conversation_wvae_bigtts
|
||||
# mix_factor: 0.4
|
||||
CosyVoiceSiliconflow:
|
||||
type: siliconflow
|
||||
# 硅基流动TTS
|
||||
@@ -840,7 +859,6 @@ TTS:
|
||||
# - "处理/(chu3)(li3)"
|
||||
# - "危险/dangerous"
|
||||
# audio_setting:
|
||||
# sample_rate: 24000
|
||||
# bitrate: 128000
|
||||
# format: "mp3"
|
||||
# channel: 1
|
||||
@@ -868,7 +886,6 @@ TTS:
|
||||
|
||||
# 以下可不用设置,使用默认设置
|
||||
# format: wav
|
||||
# sample_rate: 16000
|
||||
# volume: 50
|
||||
# speech_rate: 0
|
||||
# pitch_rate: 0
|
||||
@@ -892,7 +909,6 @@ TTS:
|
||||
host: nls-gateway-cn-beijing.aliyuncs.com
|
||||
# 以下可不用设置,使用默认设置
|
||||
# format: pcm # 音频格式:pcm、wav、mp3
|
||||
# sample_rate: 16000 # 采样率:8000、16000、24000
|
||||
# volume: 50 # 音量:0-100
|
||||
# speech_rate: 0 # 语速:-500到500
|
||||
# pitch_rate: 0 # 语调:-500到500
|
||||
@@ -1007,7 +1023,6 @@ TTS:
|
||||
protocol: websocket # protocol choices = ['websocket', 'http']
|
||||
url: ws://127.0.0.1:8092/paddlespeech/tts/streaming # TTS 服务的 URL 地址,指向本地服务器 [websocket默认ws://127.0.0.1:8092/paddlespeech/tts/streaming,http默认http://127.0.0.1:8090/paddlespeech/tts]
|
||||
spk_id: 0 # 发音人 ID,0 通常表示默认的发音人
|
||||
sample_rate: 24000 # 采样率 [websocket默认24000,http默认0 自动选择]
|
||||
speed: 1.0 # 语速,1.0 表示正常语速,>1 表示加快,<1 表示减慢
|
||||
volume: 1.0 # 音量,1.0 表示正常音量,>1 表示增大,<1 表示减小
|
||||
save_path: # 保存路径
|
||||
@@ -1031,7 +1046,6 @@ TTS:
|
||||
output_dir: tmp/
|
||||
# 以下可不用设置,使用默认设置
|
||||
# format: pcm # 音频格式:pcm、wav、mp3、opus
|
||||
# sample_rate: 24000 # 采样率:16000, 24000, 48000
|
||||
# volume: 50 # 音量:0-100
|
||||
# rate: 1 # 语速:0.5~2
|
||||
# pitch: 1 # 语调:0.5~2
|
||||
@@ -1053,7 +1067,6 @@ TTS:
|
||||
# stop_split: 0 # 关闭服务端拆句 不关闭:0,关闭:1
|
||||
# remain: 0 # 是否保留原书面语的样子 保留:1, 不保留:0
|
||||
# format: raw # 音频格式:raw(PCM), lame(MP3), speex, opus, opus-wb, opus-swb, speex-wb
|
||||
# sample_rate: 24000 # 采样率:16000, 8000, 24000
|
||||
# volume: 50 # 音量:0-100
|
||||
# speed: 50 # 语速:0-100
|
||||
# pitch: 50 # 语调:0-100
|
||||
|
||||
Reference in New Issue
Block a user