跳过主要内容

MODELS

主流语音模型目录

比较语音识别、文本转语音、实时语音、音频输入输出和供应商 API。

列表视图 / 表格视图

显示 18 / 18 个模型版本

模型家族组织提供商上下文最大输出输入输出推理工具调用结构化输出温度参数权重价格发布日期更新时间
Seedance 2.5
bytedance-seed/seedance-2-5
BSBytedance SeedSeed
-
--
----闭源暂无定价2026-07-312026-09-10
GPT-Realtime-2.1
openai/gpt-realtime-2.1
OPOpenAIGPT128K32K
--闭源
输入 $4/M · 输出 $24/M
缓存读取 $0.4/M
2026-07-062026-07-06
Gemini 3.5 Live Translate Preview
google/gemini-3.5-live-translate-preview
GOGoogleGemini131K66K
----闭源
输入 $3.5/M · 输出 $21/M
2026-06-092026-06-09
Gemini 3.1 Flash TTS Preview
google/gemini-3.1-flash-tts-preview
GOGoogleGemini8.2K16K
---闭源
输入 $1/M · 输出 $20/M
2026-04-152026-04-15
Gemini 3.1 Flash Live Preview
google/gemini-3.1-flash-live-preview
GOGoogleGemini131K66K
-闭源
输入 $0.75/M · 输出 $4.5/M
2026-03-262026-03-26
Lyria 3 Clip Preview
google/lyria-3-clip-preview
GOGoogleLyria131K66K
---闭源
输入 $0/M · 输出 $0/M
2026-03-252026-03-25
Lyria 3 Pro Preview
google/lyria-3-pro-preview
GOGoogleLyria131K8.2K
---闭源
输入 $0/M · 输出 $0/M
2026-03-252026-03-25
Seedance 2.0
bytedance-seed/seedance-2-0
BSBytedance SeedSeed
-
--
----闭源暂无定价2026-02-122026-09-10
Kling Video 3.0
kuaishou/kling-video-3-0
KUKuaishouKling Video
-
--
----闭源暂无定价2026-02-052026-09-10
Kling Video 3.0 Omni
kuaishou/kling-video-3-0-omni
KUKuaishouKling Video
-
--
----闭源暂无定价2026-02-052026-09-10
gpt-audio
openai/gpt-audio
OPOpenAIGPT128K16K
-闭源暂无定价2026-01-192026-08-06
gpt-audio-mini
openai/gpt-audio-mini
OPOpenAIGPT128K16K
-闭源暂无定价2026-01-192026-08-06
Seedance 1.5 Pro
bytedance-seed/seedance-1-5-pro
BSBytedance SeedSeed
-
--
----闭源暂无定价2025-12-152026-09-10
Sora 2
openai/sora-2
OPOpenAISora--
----闭源暂无定价2025-10-062026-09-10
Sora 2 Pro
openai/sora-2-pro
OPOpenAISora--
----闭源暂无定价2025-10-062026-09-10
Gemini 2.5 Flash TTS
google/gemini-2.5-flash-preview-tts
GOGoogleGemini33K16K
---闭源暂无定价2025-09-302026-08-06
Gemini 2.5 Pro TTS
google/gemini-2.5-pro-preview-tts
GOGoogleGemini33K16K
----闭源暂无定价2025-09-302026-08-06
Qwen-Omni Turbo
alibaba/qwen-omni-turbo
ALAlibabaQwen33K2K
--闭源
输入 $0.07/M · 输出 $0.27/M
2025-01-192025-03-26