Best Practices for Audio Integrations with Symbl

Best Practices for Audio Integrations with Symbl

Choosing the right integration approach and providing speech data to a Voice or Audio API is straight-forward if you take the time to understand the complexities and plan accordingly. These guidelines help decision-makers understand key considerations so you can move forward with a strategy that works for the long term.

Choosing the right API

Here’s a quick decision flow to help you choose the right API for your business. 

 General Best Practices

After choosing the best API for your needs, the next considerations for accuracy and efficiency are:

Sampling Rate

  • Capture the audio at the source with a sampling rate of 16,000 Hz or above when integrating over SIP.
  • Lower sampling rates may lead to reduced accuracy
  • If you cannot capture audio at the source with 16,000 Hz or higher, don’t re-sample the original audio to bump up the sample rate because this can reduce accuracy
  • Retain the original sample even if it is lower than 16,000 Hz. For example, in telephony the native rate is commonly 8000 Hz.

Audio Chunk (Buffer) Size 

  • For live audio streaming use cases (Telephony with SIP and Real-time WebSocket API), use a single audio chunk or buffer size closer to 100-millisecond for a balanced latency vs efficiency tradeoff
  • Larger chunk size in the audio is better for accuracy but will add latency

Background Noise

  • It’s best to provide audio that is as clean as possible
  • Excessive background noise and echoes can reduce accuracy
  • When possible, position the user close to the microphone 
  • If you are considering noise cancellation techniques, be aware they may result in information loss and reduced accuracy. If unsure, avoid noise cancellation.
  • Don’t use Automatic Gain Control (AGC)
  • Avoid audio clipping

Multiple People in a Single Channel

  • Ensure audio volume for each person is the same. Differing audio levels for speakers can be misinterpreted as background noise and ignored.
  • Where possible, avoid multiple speakers talking at the same time
  • Push Speaker Events to indicate the start and stop times for each person in the meeting or call.

For optimal results, consider using Real-time WebSocket API with speaker separated audio.

Calibration

  • Symbl provides the optional calibration phase that helps fine-tune the overall system to fit your preferences. Contact us to learn more.

You can learn about best practices for each API in our Documentation.

Sign up for Symbl to get 100 minutes in free trial credits so you can put these best practices to work.

Launching Async APIs for Audio files and Text

Launching Async APIs for Audio files and Text

At Symbl, we’ve always believed in building our platform working closely with our early customers. This has helped us evolve and simplify our APIs to a great extent. In this process, we realized that a lot of our customers have a lot of asynchronous conversational data. We’ve been able to accept streaming audio and generate transcripts, action items, followups, questions, summary topics in real-time with our Voice APIs. 

We observed most businesses have asynchronous conversation data in two formats

  1. Audio or Video recordings of conversations
  2. Text: Call Transcripts, Email, and Social conversations

This week, we’re launching our Async API for audio files and text. You can simply post an audio file or text payload to our rest interface and create a conversation on the Symbl Platform. Each conversation can be accessed using the Conversation API to get transcripts and other insights. For longer audio files tend to take more time to process and we have a Job API to check for the processing status. 

API Supported Format Documentation
Async Text API Messages Payload in JSON format Link
Async Audio API WAV and MPEG, Mono Audio Link

We’re confident that these APIs for asynchronous will empower businesses to extract actionable insights across many use-cases. Our customers have already started building use-cases for CRM and collaboration software using these APIs. 

As we launch the preview for these APIs, we’re excited about all the new use-cases and experiences our developer community is going to build. Here are some example use-cases

  • Automate CRM entries from email and sales calls
  • Use recorded audios to generate insights in bulk for call center process
  • Use recorded audio/video to generate post-event summaries
  • Use Zoom meeting recordings to process meeting insights 

Sign up for API preview here. You can learn more about the Async APIs on our documentation and try samples on the Postman app. We would love to hear any feedback from you and help you with any queries on your integration. 

 

Introducing the Developer Platform for Conversation Intelligence

Introducing the Developer Platform for Conversation Intelligence

 We’re excited to announce the general availability of the Symbl API Platform, the industry’s first developer platform for conversation intelligence.

Symbl offers a comprehensive suite of APIs for analyzing natural human conversations. Our APIs amplify these interactions in any channel – voice, video or text. It’s all up to you!

Built on our Contextual Conversation Intelligence (C2I) technology, you can now easily embed real-time contextual language understanding with the flexibility and control to build your own unique product experiences.

You have access to:

  • Real-time analysis of free-flowing discussions to automatically surface highly relevant summary discussion topics, contextual insights, suggestive action items, follow-ups, decisions, and questions.
  • Voice APIs that make it easy to add AI-powered conversational intelligence to telephony and WebSocket interfaces. 
  • Conversation APIs that provide a REST interface for managing and processing your conversation data.
  • Summary UI with a fully customizable and editable reference experience that indexes a searchable transcript and shows generated actionable insights, topics, timecodes, and speaker information.
  • Full documentation to get developers started with simple use cases like the post and real-time conversation summaries and other guidance.
  • Code samples – A Github repo that contains sample code snippets and apps that can be used in building conversational workflows and integrations with existing products or workflows. 
  • Flow Manager that provides a visual editor for no-code reference implementation called “Flows” for some end to end-use cases like meeting insights, Salesforce integration, Slack integration, etc.
  • Unmatched developer support with direct access to Symbl’s engineering teams and broad conversational intelligence developer community.

Sign up with Symbl to get started.
Need additional support? You can refer to our API Docs for more information and view our sample projects on Github.

 

Remember to share this post!

Announcement: Rammer.ai is now Symbl.ai

Announcement: Rammer.ai is now Symbl.ai

Understanding natural conversations to the last bit! 

It’s with tremendous gratitude and excitement that we reveal our new identity. Today we bid Rammer.ai a fond farewell.

Rammer.ai was the name chosen at inception when it was just Surbhi and Toshish launching their first startup together. It was the name that shepherded us through CorkBIC, the name that we championed during Techstars, the name that was at our side during our first venture funding round, and the name that we giddily put up on our WeWork office doors in Seattle and Pune.

Rammer is the danish word for “framework”, but unknowingly at its inception, it has some strange connotations in English (maybe even a little x-rated) that makes people question – “why that name?”. Internally we also thought there was a more relevant name out there that represented the core of what we really do…

And so, as of today — drumroll please — we are  Symbl.

#Symblers for life!

Why Symbl? 

Over the last few months, we have poured our hearts and souls into creating an identity that would closely stand for what we make and do, as well as who we are at our core. We considered 200+ candidates, had dozens and dozens of passionate pitches, and then came the deadline. We had a last intense huddle and there it was: Symbl, the one word that we all loved at once.

Symbl refers to ‘symbol’, a small semantic unit that carries high meaning intensity. In other words, when we break down language to get to the essence of meaning, a symbol is a common denominator that embodies the perception of each participant, a crucial element in untangling the subjective complexity of – say – a conversation.

We made it our mission to grow with purpose as individuals and as a team. We are empowered by these changes, with an overwhelming sense of empathy across the team.

It goes without saying that we are very excited. We thank our early customers and partners for your trust and friendship, and we look forward to being #Symblers for life!