Global-AI-Group-Inc/content-generation-skills / chatgpt/overrides/skills/mira-audio
mira-audio
VerifiedVoice, music and sound on Mira AI through its MCP server: text to speech with library voices and emotion tags in 70+ languages, multi-voice dialogue, music timed to the cut, a soundtrack the model writes by watching the clip, sound effects, voiceover and captions on a finished clip, transcripts, clean audio and stems. Use it for "voiceover", "narration", "text to speech", "TTS", "dialogue", "podcast", "music", "soundtrack", "jingle", "beat", "sound effect", "SFX", "captions", "subtitles", "transcript", "clean audio", "noise removal", "stems". NOT for the picture itself (mira-generate).
Mira audio
Every sound on Mira comes from ElevenLabs models behind the same MCP server that makes the
pictures: Eleven v4 and v4 Turbo for speech, text-to-dialogue, Music v2.5, the sound-effects model,
the voice isolator, and Scribe v2 for transcripts. A tool that
makes something returns a generation id at once and wait_for_generation brings the result: a
track is an mp3 in urls[0], an operation on a clip is a new clip, and stems, captions and
transcripts arrive as files in files[], each with a role.
Pick the tool
| The user wants | Call | Read |
|---|---|---|
| one voice reading a text: a voiceover track, narration, an ad read | generate_audio kind speech | speech.md |
| two or more people talking: a podcast, a sketch, an interview | generate_audio kind dialogue | dialogue.md |
| music with a structure, lyrics or hits on given seconds | plan_music → generate_audio kind music | music.md |
| a sound effect or an ambience bed | generate_audio kind sfx | sfx.md |
| the sounds of what happens on screen, for a silent clip | add_sound_effects | sfx.md |
| music for a clip that already exists | add_soundtrack | mix.md |
| a voice over a finished clip, captions optional | voiceover_video | mix.md |
| a library voice for the job: language, gender, age, accent, style | list_voices | voices.md |
| speech without the noise, music and echo around it | isolate_voice | mix.md |
| vocals and instruments on separate tracks | separate_stems | mix.md |
| subtitles burned in, plus an SRT | add_captions | dub-captions.md |
| a transcript, a silence cut, short clips, chapters | transcribe_video → analyze_transcript | dub-captions.md |
One file per job. Do not load them all for one track.
Sources
An operation on existing media takes exactly one of two ids: sourceGenerationId for anything
the account made on Mira (find it with list_generations, kind video or audio), or
libraryItemId for a file the user attached to the chat.
| Tool | Takes | Longest source |
|---|---|---|
add_soundtrack | a clip | 600 s |
voiceover_video | a clip | 300 s |
add_captions | a clip | 30 min |
isolate_voice | a clip or a track | 30 min |
transcribe_video | a clip or a track | 30 min |
separate_stems | a track or a clip | 600 s |
A longer source is refused (source_too_long) before a credit is spent: trim it first.
Credits
Everything that makes or changes sound spends credits; list_voices and plan_music do not. Never quote a price from memory: rates change and
estimate_cost is the only source. Speech and dialogue bill by characters, music, soundtracks
and stems by length, the operations on a clip by the source's seconds or minutes.
estimate_cost {"kind": "audio", "model": "speech", "chars": 740}
estimate_cost {"kind": "audio", "model": "music", "durationSeconds": 60}
estimate_cost {"kind": "soundtrack", "sourceSeconds": 15}
estimate_cost {"kind": "stems", "model": "6", "sourceSeconds": 180}
Workflow
- Name the job from the table. Say in one sentence what you will make and that it spends credits.
- When the user cares who speaks, call
list_voiceswith filters and offer two or three voices by name with their preview links. Otherwise leavevoiceIdempty for the default voice. - Write for the medium: text for the ear (speech.md), genre, tempo and instruments for music (music.md), a source in a space for an effect (sfx.md).
- Quote with
estimate_costbefore anything long: minutes of music, pages of text, a long voiceover. - Call, then
wait_for_generationuntil it finishes. Show the link. Do not narrate polling. - Iterate by changing one thing: one tag, one section length, one style, one voice.
Common chains
- Ad with a voice and music:
generate_video→voiceover_video(originalduck,captionson) →add_soundtrackwith mixunder, so the music dips under the new voice. - Clean up a creator clip:
isolate_voiceif the room is noisy →add_captionsfor viewers watching without sound. - Cut the picture to the music:
plan_music→generate_audiomusic → the track's URL inreferenceAudioUrlsofgenerate_videoonseedance-2-5, or into the user's editor. - Long talk to shorts:
transcribe_video→analyze_transcripttaskclipper→ cut the ranges in an editor →add_captionsstyleboldon each short.
Rules
- Speech uses the platform's library voices only. Never imitate a real person: no celebrity voices, no "sounds like" a named actor or singer. There is no voice cloning or voice design here; never offer it as a step.
- Music prompts name no artists, bands or songs and quote no existing lyrics: the provider
refuses them (
music_prompt_rejected) and suggests a rewrite. Describe the sound instead. - Speech text is written in the language it will be spoken, lyrics in the language they will be sung, music and effect prompts in English. Parameter values stay English. Reply in the user's language.
- Never show generation, voice or design ids to the user; show names and links.
When it fails
| Code | What to do |
|---|---|
text_too_long | Split at paragraph ends: v4 takes 10000 characters a call, turbo 20000, a dialogue 2000. |
source_too_long | The source is over the tool's limit in the Sources table: trim it and send the part. |
music_prompt_rejected | An artist, a song or known lyrics were recognised. Take the suggested prompt or describe the sound. |
composition_invalid | A section is outside 3-120 s or over 30 lines, or there are more than 30 sections. |
voice_not_found | The voice is not available to this account: list_voices again. |
text_moderated | The text was refused. Rewrite it; do not resend it as is. |
elevenlabs_disabled | Audio is switched off on the platform at the moment. Say so and stop. |
any other *_failed | A failed job returns its credits. Retry once, then report the code in plain words. |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |