Spiral gives your agent every tool with one account. Browse the tools →

goose · AudioReleased 2026-01-12

How to Use Scribe v2 in goose

Scribe v2 turns recorded interviews, meetings, and videos into transcripts with word timestamps and speaker labels. Unlike Scribe v2 Realtime, it focuses on long, complex recordings.

Prompts to try with Scribe v2 in goose

Copy an example into goose, or ask in your own words.

Use Scribe v2 to transcribe recordings/product-review.mp3 with speaker labels. Then compare the requested changes with this repository and draft an implementation checklist with transcript timestamps.

Scribe v2goose
Try asking
  • Transcribe recordings/demo.mp4 with Scribe v2. Then use the word timestamps to draft an SRT file and check that subtitle times increase throughout.

  • Use Scribe v2 on recordings/architecture-interview.wav with No Verbatim mode off. Then draft an architecture decision record, linking each proposed decision to a timestamp.

  • Use Scribe v2 to transcribe recordings/onboarding.mp3, specifying English as the spoken language. Then compare the transcript with docs/onboarding.md and propose corrections supported by timestamped excerpts.

  • Transcribe recordings/research-session.mp3 with Scribe v2 and speaker labels. Then create a Markdown index of user problems with timestamps, keeping your interpretations separate from transcript quotations.

How to set up Scribe v2 in goose

Pick the way that suits you. Each takes about two minutes.

Use Spiral's MCP server

  1. Add the extension

    In goose Desktop, open the sidebar, click Extensions, then Add custom extension. Enter:

  2. Sign in

    When goose first connects to Spiral, your browser opens. Sign in to Spiral, pick the organization and click Authorize. No API key. If the browser does not open, goose prints the link to open yourself.

Use the Spiral skill

  1. Send goose this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use the Spiral CLI

  1. Install and sign in

    Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

    npx -y spiral-cli@latest init

Call the Spiral API

  1. Create an API key

    In the console, under API keys.

  2. Run Scribe v2

    One request; the result comes back by polling or a webhook.

    curl https://api.spiral.ai/v1/runs \
      -H "Authorization: Bearer $SPIRAL_API_KEY" \
      -H "Content-Type: application/json" \
      -H "Idempotency-Key: $(uuidgen)" \
      -d '{
        "provider": "elevenlabs",
        "model": "scribe_v2",
        "input": {
          "file": "<file>"
        }
      }'

Then paste one of the prompts above: goose finds Scribe v2 on Spiral, shows the price and runs it.

Scribe v2 providers and prices

Spiral runs Scribe v2 through ElevenLabs. Open a card for today's price, with every fee included.

ElevenLabsAudio
Scribe v2
scribe_v2

Settings you can ask for

Scribe v2 works from your file and source URL. Ask goose for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Seed0 to 2147483647

If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be an integer between 0 and 2147483647.

Diarizeon or offoff

Whether to annotate which speaker is currently talking in the uploaded file.

File formatpcm_s16le_16 or otherother

The format of input audio. Options are 'pcm_s16le_16' or 'other' For pcm_s16le_16, the input audio must be 16-bit PCM at a 16kHz sample rate, single channel (mono), and little-endian byte order. Latency will be lower than with passing an encoded waveform.

No verbatimon or offoff

If true, the transcription will not have any filler words, false starts and non-speech sounds. Only supported with scribe_v2 model.

Temperature0 to 2

Controls the randomness of the transcription output. Accepts values between 0.0 and 2.0, where higher values result in more diverse and less deterministic results. If omitted, we will use a temperature based on the model you selected which is usually 0.

Number of speakers1 to 32

The maximum amount of speakers talking in the uploaded file. Can help with predicting who speaks when. The maximum amount of speakers that can be predicted is 32. Defaults to null, in this case the amount of speakers is set to the maximum value the model supports.

Tag audio eventson or offon

Whether to tag audio events like (laughter), (footsteps), etc. in the transcription.

Use multi channelon or offoff

Whether the audio file contains multiple channels where each channel contains a single speaker. When enabled, each channel is transcribed independently. By default a separate transcript is returned per channel; set multichannel_output_style='combined' to instead receive a single transcript with all channels merged and sorted by time. Each word in the response includes a 'channel_index' field indicating which channel it was spoken on. A maximum of 5 channels is supported. Each channel is billed independently at the full audio duration, so cost scales linearly with the number of channels.

Detect speaker roleson or offoff

Whether to detect speaker roles (agent vs customer). Requires diarize=true. Cannot be used with use_multi_channel=true. When enabled, speaker_id values will be 'agent' and 'customer' instead of 'speaker_0', 'speaker_1', etc. Usage incurs an additional 10% surcharge on base transcription cost.

Diarization threshold0.1 to 0.4

Diarization threshold to apply during speaker diarization. A higher value means there will be a lower chance of one speaker being diarized as two different speakers but also a higher chance of two different speakers being diarized as one speaker (less total speakers predicted). A low value means there will be a higher chance of one speaker being diarized as two different speakers but also a lower chance of two different speakers being diarized as one speaker (more total speakers predicted). Can only be set when diarize=True and num_speakers=None. Defaults to None, in which case we will choose a threshold based on the model_id (0.22 usually).

Timestamps granularitynone, word, or characterword

The granularity of the timestamps in the transcription. 'word' provides word-level timestamps and 'character' provides character-level timestamps per word.

Multichannel output styleseparate or combinedseparate

Controls the response shape when use_multi_channel is enabled. 'separate' (default) returns one transcript per channel under 'transcripts'. 'combined' merges all channels into a single transcript whose words are sorted by start time, each carrying a 'channel_index' - matching the single-channel response shape. 'combined' requires timestamps (timestamps_granularity must not be 'none') and does not support entity detection or redaction.

Every API field of Scribe v2 is on its tool page: open its card above.

What can you do with Scribe v2 in goose?

Turn recorded project discussions into searchable evidence for implementation work. Your coding agent can use Scribe v2 timestamps and speaker labels to connect transcript excerpts to documentation and proposed changes.

Interview transcripts for research

Use Scribe v2 to transcribe recorded interviews with speaker labels and timestamps, then have your agent organize excerpts by research question.

Podcast caption drafts

Use Scribe v2 word timestamps as the basis for captions, then have your agent group words into readable subtitle lines.

Meeting records

Create a speaker-labeled transcript with Scribe v2, then have your agent extract decisions and action items with references to the recording.

Searchable lecture archives

Transcribe recorded lectures with Scribe v2, then have your agent build a topic index linked to transcript timestamps.

Recorded call review

Use Scribe v2 to separate speakers in recorded calls, then have your agent collect timestamped examples for a reviewer to assess.

Readable dictation

Use Scribe v2 with No Verbatim mode to turn spoken drafts into text with fewer fillers and repetitions.

Multilingual content archives

Use Scribe v2 to create original-language transcripts of recordings in supported languages, then have your agent organize them for search or later translation.

Scribe v2 success rate and speed on Spiral

Success and speed over the last 24 hours, across every run of these tools on Spiral.

Success rate
99.0%
Fastest median run time
3.3s
Runs, last 24 hours
397
ToolSuccessMedian timeRuns
Scribe v299.0%3.3s397

Questions about Scribe v2 in goose

Can goose use Scribe v2?

Yes. Add Spiral to goose as an MCP server, and goose can find and run Scribe v2 like any built-in tool.

How much does Scribe v2 cost in goose?

$0.26 per hour of audio, per channel. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your goose plan is separate.

Do I need an ElevenLabs account to use Scribe v2 in goose?

No. Spiral runs Scribe v2 on its own ElevenLabs account. You sign in to Spiral once and never paste a key.

How long does it take to set up Scribe v2 in goose?

About two minutes: add the extension, then sign in.

Does goose wait while Scribe v2 runs?

Scribe v2 runs in the background. goose starts the run, checks on it and gives you the json when it's ready.

What is Scribe v2 best for?

Recorded interviews, meetings, podcasts, and videos that need searchable transcripts or captions. It is designed for long, complex recordings, while Scribe v2 Realtime targets live audio.

Which languages does Scribe v2 support, and does it translate?

Scribe v2 supports more than 90 languages and transcribes speech in the language spoken. Translation requires a separate step.

Can Scribe v2 separate speakers?

Scribe v2 supports speaker diarization for up to 32 speakers. Review labels where people interrupt or speak over one another.

How long can a recording be?

ElevenLabs documents up to 15 hours per recording in standard transcription mode.

Can Scribe v2 remove ums and repeated phrases?

Yes. No Verbatim mode removes filler words, repeated phrases, and stuttering; keep it off when you need to study the original wording and delivery.

Get started

Start using Scribe v2 in goose

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into goose:

Set up goose

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options