Academy
My learningOpen Scenario

Audio on Scenario, models and prompts

The audio jobs you can run on Scenario, where each one lives in the app, how to choose a model, and how to write a prompt for music, speech and sound effects.

  • Lesson 1 of 5
  • Checked Nov 11, 2026
Tutorial film2:41 Captions
Audio on Scenario, models and prompts

Watch the video: https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/a28e6fc0ac5ca353279f56b14b5428955dab1af141a8ad6b14b4db296fcc60f3.mp4

About this lesson

Audio on Scenario isn't one tool. It's a set of jobs, each with its own models: make music, speech and sound effects, change a voice you already have, and read audio back as text. This lesson shows where each job lives in the app, how to find a model by job, how to write the prompt each kind of model expects, and how to check a take. The example is one short narration line made with ElevenLabs v4 and checked with Gemini 3.5 Transcribe. The models and settings in this lesson are as of November 2026.

See moreSee less
  • Audio is a set of separate jobs, each with its own models: music, speech, voices, effects and transcripts.
  • Pick the job first, then the model, then write the prompt the way that model reads it: a description for music and effects, the script itself for speech.
  • Audio is the cheapest modality, so take several; listen to each one alone and check it by transcribing it.
Step by step with an agent, through the Scenario MCP (6 steps)Hide the steps

  1. Connect the Scenario MCP

    Connect your agent and sign in once at mcp.scenario.com. Then tell it which Scenario team and project to use, so every file lands there.

  2. Pick the job, then the model

    Say which job you need (music, speech, a voice change, an effect or a transcript) and ask the agent to rank models for it with recommend, which is free. The brief below uses the lesson's narration line.

  3. Brief the agent: a speech take

    Prompt
    Make one narration take with ElevenLabs v4 (model_elevenlabs-tts-v4). Read model_schema_get first for the parameter names. Public voice Alice, Stability 0.5, Similarity Boost 0.75, output format MP3 44100Hz 128. Put only the script in the text field, word for word; the tags in square brackets set the delivery and are not read aloud:
[calm] Every evening at six, the keeper climbs the hundred and twelve steps of the lighthouse. [short pause] The lamp is old, the stairs are older, and the cat, as usual, is already at the top.

Quote the cost with a dry run first and wait for my go.

  4. Check the take by transcribing it

    Prompt
    Wait for the job with jobs_wait and show me the take with asset_display. Then transcribe it with Gemini 3.5 Transcribe (model_google-gemini-3-5-transcribe), default settings. Report the take's length and the transcript next to the script, word by word. Quote the cost with a dry run first and wait for my go.

  5. Accept or redo

    Accept when the speech matches the script word for word with the delivery you asked for and the length is what you expect. Reject missing, swapped or mispronounced words, or a tag read aloud; ask for a new take of that line only.

  6. File and report

    Prompt
    Create a collection for this lesson with the approved take and its transcript, and report the models, the settings and every asset ID.
Step by step in the web app (6 steps)Hide the steps

  1. Open the audio panel

    Create › Audio opens on a speech model, Gemini 3.8 Flash TTS, with Text, Voice, Multi-speaker and Language. Transcription is not here: it lives under Create › Text.

  2. Find a model by job

    Click the model name › View all models, tick Audio under Output, then one capability at a time: Speech, Music, Sound Effects or Tools. Click a model to read it, then Use this model.

  3. Read the field's name

    The main field is called Music Description, Sound Description or Text, depending on the model. A speech model reads Text aloud, so choose the voice in the voice setting and never describe it in the text.

  4. Write a speech take

    ElevenLabs v4, Public Voice Alice, Stability 0.5, Similarity Boost 0.75, Output Format MP3 44100Hz 128. Type the script in Text, with delivery tags in square brackets, and click Generate.

    Prompt
    [calm] Every evening at six, the keeper climbs the hundred and twelve steps of the lighthouse. [short pause] The lamp is old, the stairs are older, and the cat, as usual, is already at the top.

  5. Prompts for music and effects

    For music, lead with genre, mood and tempo, then the instruments, the structure and the ending; for an effect, name the source, the action and the space. End both with what to leave out.

    Prompt
    Short warm orchestral title cue for an animated short about a lighthouse and its cat. 90 BPM, D major. Pizzicato strings and glockenspiel, then a gentle clarinet melody. Clean final chord, no fade-out. Instrumental only, no vocals.

A heavy wooden door with iron hinges creaks open slowly, then closes with a solid thud, inside a stone hallway with a short echo. No music, no voices.

  6. Check the take

    Read the length on the take's card first (here 00:12). Then Create › Text › Gemini 3.5 Transcribe, Audio › Select from Library, Generate, and compare the transcript with the script; an instrumental should transcribe to nothing.

Related

Read the full article10 min read
CoursesLessonsBrowseMy learning