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

Claude Code · Audio

How to Use Canary Speech-to-Text in Claude Code

Canary Speech-to-Text turns recordings into transcripts for notes and searchable archives. It shares Canary Speech-to-Text Turbo's documented transcript format, so choose by testing the same recording in both.

Prompts to try with Canary Speech-to-Text in Claude Code

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

Use Canary Speech-to-Text to transcribe recordings/bug-report.wav with punctuation and capitalization enabled. Compare the reported behavior with the relevant code and draft a bug report that separates observations from hypotheses.

Canary Speech-to-TextClaude Code
Try asking
  • Use Canary Speech-to-Text to transcribe recordings/architecture-review.wav. Keep the transcript unchanged, then draft an architecture decision record using the project's existing template; mark unresolved choices as open.

  • Use Canary Speech-to-Text to transcribe recordings/test-dictation.wav twice, with punctuation and capitalization enabled and disabled. Show the text differences and recommend which result fits our transcript search feature.

  • Read this paragraph aloud with Canary Speech-to-Text in a calm, warm voice and give me the MP3. Save the result in ./assets.

  • Make a 30-second podcast intro voiceover with Canary Speech-to-Text.

How to set up Canary Speech-to-Text in Claude Code

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

Use Spiral's MCP server

  1. Add the hosted server

    This adds Spiral to the current project. Add --scope user to use it in every project.

    claude mcp add --transport http spiral https://api.spiral.ai/mcp
  2. Sign in

    Start claude, type /mcp, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.

Use the Spiral skill

  1. Send Claude Code 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 Canary Speech-to-Text

    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": "fal",
        "model": "fal-ai/speech-to-text",
        "input": {
          "audio_url": "https://storage.googleapis.com/falserverless/canary/18e15559-ab3e-4f96-9583-be5ddde91e43.mp3"
        }
      }'

Then paste one of the prompts above: Claude Code finds Canary Speech-to-Text on Spiral, shows the price and runs it.

Canary Speech-to-Text providers and prices

Spiral runs Canary Speech-to-Text through fal. Open a card for today's price, with every fee included.

falAudio
Speech-to-Text
fal-ai/speech-to-text

Settings you can ask for

Canary Speech-to-Text works from your audio path. Ask Claude Code for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Use Punctuation/Capitalization (PnC)on or offon

Whether to use Canary's built-in punctuation & capitalization

Every API field of Speech-to-Text is on its tool page: open its card above.

What can you do with Canary Speech-to-Text in Claude Code?

Turn recorded product discussions and spoken bug reports into text you can compare with the project's code and documentation. Use Canary Speech-to-Text for transcription, then have the coding agent trace claims to files and draft changes for review.

Interview transcript drafts

Transcribe a recorded interview before selecting quotes or writing an article. Check selected quotes against the recording and verify who said them.

Searchable podcast archives

Create a text companion for each recorded episode, then index the transcripts by episode. Keep episode references with search results.

Meeting notes

Turn a meeting recording into a transcript, then ask your agent to extract decisions and open questions. Leave ownership unassigned when the transcript does not establish it.

Voice memo organization

Transcribe spoken ideas, then have your agent sort the text into tasks, questions, and reference notes. Keep the original transcript alongside the organized version.

Lecture study notes

Make a transcript of a recorded lecture, then build an outline and study questions from it. Review technical terms against the recording before relying on them.

Subtitle text preparation

Prepare transcript text for an editor or alignment tool. Add timing separately before exporting captions.

Questions about Canary Speech-to-Text in Claude Code

Can Claude Code use Canary Speech-to-Text?

Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Canary Speech-to-Text like any built-in tool.

How much does Canary Speech-to-Text cost in Claude Code?

Up to $0.0624 per run at the default inputs for 60 seconds of input. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.

Do I need a fal account to use Canary Speech-to-Text in Claude Code?

No. Spiral runs Canary Speech-to-Text on its own fal account. You sign in to Spiral once and never paste a key.

How long does it take to set up Canary Speech-to-Text in Claude Code?

About two minutes: add the hosted server, then sign in.

Does Claude Code wait while Canary Speech-to-Text runs?

Canary Speech-to-Text runs in the background. Claude Code starts the run, checks on it and gives you the json when it's ready.

What does Canary Speech-to-Text return?

It returns transcription text. Treat that transcript as the source material for a separate summary, action list, or edited article.

Does Canary Speech-to-Text identify speakers?

The documented output does not include speaker labels. For interviews and meetings, avoid assigning statements to named people unless you verify who said them.

Can Canary Speech-to-Text produce timed subtitles?

Use the transcript as a subtitle draft, then add alignment in a separate step. The documented output does not include word timestamps, so do not estimate subtitle timing from the text alone.

When should I use automatic punctuation and capitalization?

Use it for transcripts you plan to read, review, or turn into notes. If another processing step handles punctuation and capitalization, compare results with it disabled before choosing.

How should I compare Canary Speech-to-Text and Canary Speech-to-Text Turbo?

Their documented transcript formats match. Run the same representative recordings through both and compare missed words, names, numbers, and sentence breaks before choosing.

Get started

Start using Canary Speech-to-Text in Claude Code

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

Paste this into Claude Code:

Set up Claude Code

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