enhance：add mimo-v2.5-tts provider#19
Open
Rocke1001feller wants to merge 1 commit into
Open
Conversation
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
Adds a new MiMo TTS provider to the web-video-presentation skill and updates documentation to reflect the additional built-in provider.
Changes:
- Introduce
mimo.shprovider (curl + jq) that calls MiMo-V2.5-TTS and converts returned base64 WAV to mp3. - Update provider documentation and references to list MiMo as a built-in option.
- Add usage instructions for MiMo (env vars, voices, base URL clusters).
Reviewed changes
Copilot reviewed 6 out of 6 changed files in this pull request and generated 9 comments.
Show a summary per file
| File | Description |
|---|---|
| skills/web-video-presentation/templates/scripts/tts-providers/mimo.sh | New MiMo-V2.5-TTS provider implementation (request, decode, convert). |
| skills/web-video-presentation/templates/scripts/tts-providers/README.md | Document MiMo as an additional built-in provider + add usage section. |
| skills/web-video-presentation/references/AUDIO.md | Update “built-in providers” list to include MiMo. |
| skills/web-video-presentation/SKILL.md | Update skill description + internal docs to mention 3 built-in providers. |
| skills/web-video-presentation/README.zh-CN.md | Update top-level Chinese README to mention MiMo provider. |
| skills/web-video-presentation/README.md | Update top-level English README to mention MiMo provider. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| # Write response (JSON with base64 audio) to a temp file, then decode. | ||
| # MiMo API returns: {choices:[{message:{audio:{data:"<base64>"}}}]} | ||
| local tmp | ||
| tmp=$(mktemp -t mimo.XXXXXX.json) |
|
|
||
| # Decode the base64 WAV from JSON → write raw WAV → convert to mp3 | ||
| local raw_wav | ||
| raw_wav=$(mktemp -t mimo.XXXXXX.wav) |
| # Decode the base64 WAV from JSON → write raw WAV → convert to mp3 | ||
| local raw_wav | ||
| raw_wav=$(mktemp -t mimo.XXXXXX.wav) | ||
| jq -r '.choices[0].message.audio.data' "$tmp" | base64 -d > "$raw_wav" |
Comment on lines
+94
to
+97
| curl -fsS -o "$tmp" -X POST "$base/chat/completions" \ | ||
| -H "api-key: $MIMO_API_KEY" \ | ||
| -H "Content-Type: application/json" \ | ||
| -d "$payload" 2>/dev/null |
Comment on lines
+105
to
+109
| ffmpeg -y -i "$raw_wav" -codec:a libmp3lame -qscale:a 2 "$out" >/dev/null 2>&1 | ||
| local code=$? | ||
|
|
||
| rm -f "$tmp" "$raw_wav" | ||
| return $code |
Comment on lines
+80
to
+81
| # MiMo uses the Chat Completions format: text goes in role=assistant, | ||
| # voice/style goes in role=user. For preset voices, audio.voice is set. |
| --arg t "$text" \ | ||
| --arg v "$voice" \ | ||
| --arg m "$model" \ | ||
| '{model:$m, messages:[{role:"user", content:""}, {role:"assistant", content:$t}], audio:{format:"wav", voice:$v}}') |
| | `openai.sh` | OpenAI Audio Speech API | `OPENAI_API_KEY` env var | curl-based；多数 agent 已有 key | | ||
| | `mimo.sh` | MiMo-V2.5-TTS API | `MIMO_API_KEY` env var | curl-based；9 preset voices；中文口播强 | | ||
|
|
||
| 只内置这两个 —— 我们不替你做更多技术选型。其它后端的代码片段在下面， |
Comment on lines
+66
to
69
| │ └── tts-providers/ # 每 provider 一个 .sh（内置 3 个） | ||
| │ ├── README.md # 三函数契约 + 5 段现成代码片段（11labs / edge-tts / say / azure / gcloud） | ||
| │ ├── minimax.sh # 默认 provider，用 mmx-cli | ||
| │ └── openai.sh # 内置 OpenAI TTS（curl + OPENAI_API_KEY） |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Add MiMo-V2.5-TTS as a built-in TTS provider (tts-providers/mimo.sh), alongside the existing minimax and openai providers.
Why
What changed
Usage
export MIMO_API_KEY=tp-... # get one at https://platform.xiaomimimo.com
PRESENTATION_TTS=mimo npm run synthesize-audio