We count page visits with Google Analytics to see which pages are read. Nothing is stored until you accept, and we never store search queries. Privacy .
Accept analytics Decline
wellknown A live, machine-queryable index of AI agents, MCP servers and tools. Every record separates what publishers declare from what we observed.
Records are indexed from public sources and attributed to them. Observed data is ours; declared data is theirs. Privacy Terms v0.1 · early network
370.ai — AI Gateway: 100+ Chat Models, Image & Speech Generation — history · Wellknown
Index / 370.ai — AI Gateway: 100+ Chat Models, Image & Speech Generation / History Append-only ledger
370.ai — AI Gateway: 100+ Chat Models, Image & Speech Generation Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
4 events · 1 tool-surface change JSON Copy curl Tool surface changed
2026-10-03 18:29 UTC · 19 d ago Changed the definition of "list_models" and "text_to_speech"
list_models changed
description
List theevery AImodel modelsid availableyour API key can call on 370.ai (chat / image / video ⟨6 unchanged words⟩ 12 words differ · removed · added
text_to_speech changed
description
Convert text to spoken audio. ReturnsBilled aper statusinput withcharacter byteon size.your key.
Args:
text: the text to speak.
voice: ⚠️ 当前默认模型voice (qwen3-tts-flash)id. **忽略The OpenAI 音色名**voice ——
names ( alloy / echo / fable / onyx / nova / shimmer ) 六个会被统一改写成同一个音色are
accepted TLS
2026-09-14 17:22 UTC · 1 mo ago Certificate recorded, valid to 2026-11-05
Authorization
2026-09-14 17:22 UTC · 1 mo ago Authorization not required
Tool surface
2026-09-12 16:26 UTC · 1 mo ago First tool surface recorded: 4 tools (server version 1.27.2)
Showing the latest 4 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
,
but on the default model they are all mapped to the same default voice, so
传哪个都得到逐字节相同的音频。要真正换音色请传上游音色名
they
sound identical. To pick a different voice, pass a voice id supported by the model
(
如
for
the default model, e.g.
Cherry
/
or
Ethan)
。
.
Returns a short status line plus the generated audio as an audio content block
(mimeType as returned by the gateway, e.g. audio/mpeg).
102 words differ · removed · added
outputSchema
before
{"properties":{"result":{"title":"Result","type":"string"}},"required":["result"],"title":"text_to_speechOutput","type":"object"}after
—