TEN Framework

by Agora

Don’t want to install TEN Framework? Drop the file here.

The first 20 minutes of any recording are transcribed free: a recording up to 20 minutes transcribes in full, a longer one is previewed, and a pack from $6 (500 minutes) transcribes the rest and opens every export, and credits never expire.

Open-source framework by Agora for building realtime multimodal voice AI agents.

Linux, macOS, Cloud  ·  free

TL;DR

Best for builders on Agora RTC who want an OSS voice/video agent runtime. Pricing: free.

Category
Open source
License
NOASSERTION
Stars
★ 11.0k
Last push
2026-08-06
Pricing
free
Platforms
Linux, macOS, Cloud

What it is

TEN (The Embodied Network) is Agora's open-source framework for realtime multimodal agents over its global RTC SDK. It abstracts ASR, LLM, TTS, and video components into reusable extensions and is positioned alongside Pipecat and LiveKit Agents as an OSS alternative for voice-agent runtime. Apache-2.0 licensed.

Best for: Builders on Agora RTC who want an OSS voice/video agent runtime.
Watch out for: Newer project; ecosystem narrower than Pipecat or LiveKit Agents.

What people actually do with TEN Framework-style transcription

The tool is the means. These are the jobs — each one priced at published rates, each one wired up on its own page.

Wire it into Amazon S3n8nMake.comGoogle DriveZapierSlack

Features

Speaker diarizationNo
Word-level timestampsNo
Streaming / real-timeNo
Languages supportedNone
HIPAA eligibleNo

Links

GitHub repo ↗

TEN Framework vs Whipscribe

FeatureTEN FrameworkWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree$6–$24 one-time packs (credits never expire) · first 20 minutes free
Speaker identification—Named in the summary, key quotes and chapters
Word timestamps—Yes
Streaming—No
Languages—99
PlatformsLinux, macOS, CloudWeb, API, MCP

Alternatives to TEN Framework

Frequently asked about TEN Framework

Is TEN Framework free?

Yes. TEN Framework is free and open source.

Does TEN Framework work on Mac, Windows and Linux?

TEN Framework runs on Linux, macOS and Cloud.

Does TEN Framework identify different speakers?

No. TEN Framework does not label speakers; a conversation comes back as one continuous text. If you need speaker labels, that is a separate tool or a different service.

Does TEN Framework give word-level timestamps?

No — TEN Framework produces segment or sentence timing only, so subtitle cues can land mid-word.

Can TEN Framework transcribe live audio?

No — TEN Framework works on finished files, not a live stream.

Is TEN Framework HIPAA compliant?

TEN Framework does not claim HIPAA compliance. For PHI, run it on infrastructure you control or choose a service that will sign a BAA.

What are the limitations of TEN Framework?

Newer project; ecosystem narrower than Pipecat or LiveKit Agents.

Who is TEN Framework best for?

Builders on Agora RTC who want an OSS voice/video agent runtime.

Does TEN Framework run offline?

TEN Framework runs on your own machine — it is open source, so nothing leaves the computer unless you configure it to.

Can I use TEN Framework in the browser?

No — TEN Framework is a Linux, macOS and Cloud application, not a web app. You install it rather than sign in to it.

Where is the TEN Framework source code?

On GitHub at github.com/TEN-framework/TEN-framework. It is maintained by Agora.

What kind of tool is TEN Framework?

In this directory TEN Framework is filed under voice middleware, voice agent, developer framework as a open-source tool.

What are the alternatives to TEN Framework?

There is a side-by-side page at /tools/ten-framework-alternatives comparing TEN Framework with the closest tools in the same category on price, platform and features.

Can I automate TEN Framework-style transcription without running it myself?

Yes. If what you want is transcripts rather than the tool itself, Whipscribe does the same job as a hosted API: submit a file or URL, poll a job id, pull the result as txt, json, srt, vtt or docx. $0.012 a minute — about $0.72 an audio hour — bought as credits that never expire. The automation recipes on this site show it wired to Drive folders, Zoom recordings, S3 buckets and no-code platforms.

How is Whipscribe different from TEN Framework?

TEN Framework is something you run; Whipscribe is something you call. Recordings are transcribed on our own servers and never used for training, and every job returns five formats plus an AI summary, quotes and topics. The first 20 minutes of any recording are transcribed free, and a pack from $6 (500 minutes) transcribes the rest and opens every export.

Whipscribe is a hosted transcription service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.

Transcribe your recordings

Explore

Have the recording already?

Skip the setup and send the file or the link: see how to transcribe an MP3 of any length, how to transcribe a podcast and the SRT file generator.

Looking at paid options?

Before you choose a transcription tool or service: see an honest roundup of the best transcription services, affordable transcription priced per hour and transcription services from $6.