Hamsa Media · API

Media Platform API

The same engine behind the media studio, as a jobs API: submit audio for transcription, text for speech, and transcripts for AI-generated content — then list, inspect and manage every job from your backend.

  • Transcription jobs
  • Text-to-speech jobs
  • AI content from transcripts
  • Webhook delivery
  • Full job management

Capabilities

The studio’s workloads, as API jobs

01

Transcription by URL

Point the transcribe endpoint at a hosted audio or video file and get back a timestamped, speaker-separated transcript — with SRT subtitles if you ask.

02

Speech generation

The text-to-speech jobs endpoint turns scripts into audio in the voice and dialect you pick, including voices you cloned.

03

AI content from transcripts

Generate structured content from completed transcriptions — with ready templates or your own custom prompt — through the AI content endpoints.

04

Costs known up front

The estimate endpoint prices an AI content job before you run it, so pipelines can decide before they spend.

05

Jobs you can manage

List jobs, view one with its results, update it or delete it — the job store behind the studio is fully exposed.

06

Results pushed to you

Jobs deliver to your webhookUrl with optional webhook authentication, or you poll by job ID — your pipeline picks the pattern.

Integration

A media pipeline, request by request

How recorded content moves through the API.

  1. 01

    Create a secret key

    Create a secret key in the dashboard and keep it on your server. Every request carries it in the Authorization header as Token <key>.

  2. 02

    Submit the media

    POST the file’s URL to the transcribe endpoint with a model and language. The job queues and runs asynchronously.

  3. 03

    Receive the transcript

    The completed transcription lands on your webhook, or you poll the job — timestamped segments, speakers, and SRT if requested.

  4. 04

    Generate what comes next

    Feed the transcription to the AI content endpoints for summaries and structured documents, or send a script to the TTS jobs endpoint for narrated audio.

  5. 05

    Keep the job store clean

    List what has run, inspect results by ID, update titles and metadata, and delete jobs your pipeline no longer needs.

Reference

The media platform API at a glance

Each row links to its page in the API docs — the authoritative reference, with full schemas and runnable code samples.

AreaDetail
TranscriptionA hosted media file in, a timestamped transcript out — with SRT subtitles if requested
Text to speechScripts to audio in the voice and dialect you choose, delivered async
AI contentStructured content from transcripts, with ready templates or your own custom prompt
Cost estimatePrice an AI content job before you run it
From transcriptsGenerate content directly off a completed transcription
Job managementList jobs, view one with its results, update it or delete it
DeliveryWebhook with optional authentication per job, or polling by job ID
ModelsSTT: Hamsa-General-V2.0 and Hamsa-Conversational-V1.0; TTS voices from the catalog or cloned
AuthenticationA secret key in the Authorization header of every request, as Token <key>

Use cases

Pipelines teams run on the media API

01

Publish-time transcription

New episodes and videos are transcribed as they are published, and the transcript lands in your CMS beside the media.

02

Subtitle automation

Every video that enters your library leaves with tuned SRT subtitles, without an editor opening a tool.

03

Content repurposing

A recorded webinar becomes a summary, an article and social posts through the AI content endpoints — from one transcription job.

04

Voice-over generation

Scripts from your localization flow go in, narrated Arabic audio in the right dialect comes out, delivered to your storage by webhook.

FAQ

Questions about the media platform API

How does the API relate to the media studio?

+

Same engine, two surfaces. The studio is the web workspace for people; the API runs the same transcription, speech and AI content workloads headless, from your own backend, with jobs as the shared currency.

How do results get delivered?

+

Each job accepts a webhookUrl, with optional webhook authentication, and posts the result there when it completes. Prefer pulling? Poll the job by its ID instead.

What can the AI content endpoints produce?

+

Structured written content generated from a completed transcription — using ready templates or a custom prompt you pass to the /custom endpoint. The /estimate endpoint prices the job before you run it.

Can I use cloned voices in TTS jobs?

+

Yes. Create the voice through the voice cloning API, preload it once, and use its ID as the voiceId on text-to-speech jobs.

How is the API authenticated?

+

With a secret key created in the dashboard, sent in the Authorization header as Token <key>. It is shown once and refused from a browser, so keep it on your server. Keys are project-scoped, so jobs land in the project the key belongs to.

Keep reading

Partner ecosystem

Trusted Across the
Technology Ecosystem

Hamsa works with leading technology companies, integrators, and solution providers to bring enterprise Voice AI to organizations across the region.