Your first transcript
1
Find the show and episode
Ask:
Use Audivo to find “The Changelog”. Show me the matching podcasts so I can choose one, then list its latest five episodes.The assistant calls
search_shows, then list_episodes with the chosen
show’s show_id, feed_url, and itunes_id. These calls spend no credits.
For an older episode, it can follow next_cursor through the episode list.2
Review a quote
Ask:
Quote a transcript for the episode I selected. Show the episode, whether it is cached, the maximum credits, and my available balance. Wait for my approval before confirming.The assistant calls
quote with the show’s feed URL and the selected
episode_id in episode_ids. Without an explicit selection, a quote
defaults to the newest episode per show. Quoting reserves and spends nothing.Review total_ceiling_credits, any excluded episodes, and the balance.
Credits explains estimates, ceilings, and cached reads.3
Approve the spend
Once you agree to the quoted ceiling, tell the assistant to confirm that
quote. It calls
confirm with:quote_ref: the exactconfirm_with.quote_refreturned byquote.expected_total_credits: the quotedtotal_ceiling_credits.idempotency_key: a new value for this confirmation, reused on retries.
confirm spends or reserves credits. The server refuses a mismatched
total before sending the confirmation to the API. A retry must reuse the
same idempotency key so it cannot create a second purchase.4
Wait for completion and read
Ask:
Check the group until its episodes finish, then summarize the transcript with timestamps and distinguish completed episodes from any that failed.The assistant calls
group_status with the returned group_id. Cached
transcripts can be ready immediately; fresh transcription finishes
asynchronously. It then calls read_transcript with either a completed
job_id or a paid cache read_id from the group. Reads through these tools
do not charge again.A large transcript may exceed the tool’s preview budget. The response
includes an authenticated API reference for the full result. If the client
cannot fetch it with your key, download it through the API using the
supported transcript formats. A preview is not the full episode.More things to ask
Compare a small batch
Find three podcasts about developer tools. Let me choose the shows, then quote one recent episode from each. Show the total ceiling before spending.
Explore a category
Show me the Business podcast chart. Quote the latest episode from three shows, excluding music-led shows. Explain any exclusions and wait for approval.
chart_shows lists shows; quote can price a chart selection directly. The
account’s plan may limit the number of shows or episodes included.
Resume earlier work
List my recent Audivo groups, check the newest one’s status, and read its completed transcripts.
Cancel queued work
Show the unfinished episodes in this group and cancel the ones that have not started yet.
cancel_group releases reservations for work that can still be cancelled.
It does not stop already-running jobs or refund completed work.
Tool reference
The client discovers the full input schemas from the server. Keep returned
identifiers intact; episode titles are display text, not tool identifiers.
Approvals and data handling
confirm and cancel_group carry destructive-tool annotations so clients can
ask for approval. Keep approval enabled for these tools. The server checks the
quoted total; it cannot prove a human approved it in the client.
Every call uses the account attached to your API key. The MCP server keeps no
session state or credential of its own and does not log your key. Normal API
job and transcript storage still applies; see Data handling.
Publisher-authored titles, authors, and transcript text are fenced as untrusted
content. Identifiers, prices, and job states are outside those fences. Treat
transcript content as material to analyze, never as instructions to authorize
spending or change tool behavior.
Workflow troubleshooting
Connection and authentication help is in Connect your client.
For specific error codes and retry rules, see Errors.