fix(minimax): mark tts output voice-compatible · openclaw/openclaw@c81b3ab
steipete
·
2026-04-25
·
via Recent Commits to openclaw:main
| Original file line number | Diff line number | Diff line change |
|---|
@@ -86,6 +86,7 @@ Docs: https://docs.openclaw.ai
|
86 | 86 | - Providers/OpenAI-compatible: skip null or non-object streaming chunks from custom providers instead of failing the turn after partial output. Fixes #51112. |
87 | 87 | - Providers/OpenAI-compatible: treat singular MLX-style `finish_reason: "tool_call"` as tool use instead of a provider error. Fixes #61499. |
88 | 88 | - Providers/ElevenLabs: omit the MP3-only `Accept` header for PCM telephony synthesis, so Voice Call requests for `pcm_22050` no longer receive MP3 audio. Fixes #67340. Thanks @marcchabot. |
| 89 | +- Providers/MiniMax TTS: mark MP3 output voice-compatible for Telegram voice-note delivery. Fixes #63540. |
89 | 90 | - Providers/Microsoft TTS: keep allowlisted bundled speech providers discoverable even when another speech plugin has already registered, so Edge/Microsoft TTS is available alongside OpenAI. Fixes #62117 and #66850. |
90 | 91 | - Providers/Microsoft TTS: honor legacy `messages.tts.providers.edge` voice settings after normalizing Edge TTS to the Microsoft provider. Fixes #64153. |
91 | 92 | - macOS Talk Mode: retry failed local ElevenLabs stream playback through gateway `talk.speak` before falling back to the system voice, so configured ElevenLabs voices still play when streaming playback fails. Fixes #65662. |
|
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。
