# Keep the detail that helps you improve. Review recorded audio and transcripts alongside the call that produced them. Follow processing status, find the detail that matters and give your team the context to improve the next conversation. [Start for Free](/dashboard/signup?returnTo=%2Fdashboard%2Fw%2Fvoice%2Fcalls) [Contact sales](/demo?product=voice-recordings) ## Set up with your agent [Read the agent setup guide](/docs/ai/set-up-your-agent) Copy this prompt into your coding agent: ```text Bird connects customer communications, data and automation. Help me build with Bird using my coding agent. 1. Read https://bird.com/docs/ai/set-up-your-agent.md and follow its setup workflow for this client. Use an existing connected Bird MCP server or signed-in CLI when available. 2. Read the product guide for the task I want to complete and inspect my existing integration. Identify the workspace, available operations and required setup. 3. Help me complete a first example for the product and destination I choose. Follow the operation through to its actual result, explain any uncertainty, and help me choose the next step. First task: Identify the calls to record, consent workflow, access and retention needs. Read the recording guide and prepare a controlled capture and retrieval test. First use the connected Bird MCP server or signed-in CLI for a read-only inventory. Discover the available tools and read their schemas or help; do not invent call-control operations. If neither surface is available, follow https://bird.com/docs/ai/set-up-your-agent.md. Read the linked guides through their .md alternatives. Present the exact target and configuration before changing routing, placing calls, recording audio, purchasing numbers or submitting a port. Obtain my approval for those actions. Use this Bird page as the starting context: https://bird.com/products/voice/recordings Read its Markdown alternative and linked guides. Keep the first example relevant to this page and the customer outcome I choose. Preserve the supplied campaign context when following Bird signup or sales links. ``` The conversation, with its context Call session · appointment reminder Caller response 00:18 A specific capture The recording belongs to the call leg that produced it. Transcript ready “Friday morning works for me. Please ask the team to call me back.” Use the source recording to review a detail that matters. Illustrative recording and transcript. No customer audio or live processing. Trusted every day by teams that build world-class software [Read more customer stories](/customers) - [Airwallex](/customers/airwallex) - [Glovo](/customers/glovo) - [Zillow](/customers/zillow) - Uber - [Binance](/customers/binance) - Adobe - Meta - PayPal - Pinterest - Square - [Al Jazeera](/customers/aljazeera) - [Aramex](/customers/aramex) - [Bazaar Technologies](/customers/bazaar) - [ComparaOnline](/customers/compara) - [Emma](/customers/emma) ## What should you retain from the call? Choose the audio needed for your use case and make recording behavior explicit in the call design. A caller response, voicemail and full conversation are different capture requirements. Confirm the supported source and recording bounds before designing a review process around them. ### Make recording deliberate Start recording deliberately and stop the active capture before sensitive input. A sequence captures audio received from the participant; generated prompts are separate. Keep the resulting recording identity with its source call. ### Choose transcription separately Capturing audio and processing speech are separate operations. Request a transcript when it serves the workflow, then inspect its completion or failure status. ## A session connects the calls and their artifacts. Start with the session to understand the overall interaction, then inspect each call leg and its recordings or transcripts. Artifacts belong to the calls that produced them. A forwarded session may contain several legs with different outcomes and available evidence. - **01** Keep incomplete states visible: No transcript, pending processing and a failed transcription mean different things. Show the recorded state rather than treating an empty text field as proof that nothing was said. - **02** Allow for later processing: A call can end before its transcript is ready. Revisit the retained record when processing completes instead of delaying the call outcome until every artifact is available. ## Give the next person enough context. Use the audio and transcript to locate the point a customer needed help, confirm the recorded facts and improve the call experience. Keep any generated summary separate from the source evidence and confirm important business outcomes in the application that owns them. ### Control who can review Use workspace permissions to limit access and set an appropriate retention policy for your operation. Include notice and consent in the calling experience where required. ### Measure what improved Compare the observed issue before and after a prompt or routing change. More recordings do not by themselves establish better service or a higher conversion rate. ## Questions about recordings and transcripts ### Is every call automatically recorded? No. Recording is an explicit part of the configured workflow. Decide which supported source to capture and when capture starts and stops. ### Does a recording automatically create a transcript? Audio capture and transcription are separate operations. Request transcription where appropriate and inspect its processing result. ### Can a transcript arrive after the call ends? Yes. Speech processing can finish after the telephone call. Keep call outcome and artifact processing state distinct. ### Does one session mean one recording? No. A session can correlate several call legs, and each may have its own artifacts. Inspect the source call and capture identity. ### Can I treat a transcript as a confirmed customer action? Use it as conversation evidence. Confirm a booking, order change or payment in the business system that executed that action. ## Build the next part of your calling path [Recordings and transcripts guide](/docs/guides/voice/recordings) Follow the setup, requirements and operational checks. [Call sequences](/products/voice/call-sequences) Turn prompts, keypad choices and named branches into a versioned workflow. [AI Voice](/products/voice/ai-voice) Bring a conversational runtime to the phone, with your context, tools and handoff. [Voice pricing](/pricing/voice) Review published destination rates and relevant call components. ## Make the call useful after it ends. Choose which conversations to record, who needs access and how long the evidence should remain available. Test consent, capture and retrieval as one workflow. [Read the recording guide](/docs/guides/voice/recordings) ## Related resources - [Voice overview](/docs/guides/voice/overview) (docs) - [What is a voice API?](/explained/voice/what-is-a-voice-api) (answer) - [Voice](/products/voice) (product) [Get an implementation brief](/learn/workspace?topic=voice)