Transcription API plus the AI platform built on top of it.
En račun vam daje dostop do API-ja, MCP strežnika, CLI in polnega vmesnika delovnega prostora. Plačilo po porabi brez minimumov, brez roka za potečenje vašega kreditnega stanja in brez potrebe po kreditni kartici za začetek.
Most transcription APIs make you choose. You don’t have to.
Ko se odločite za transcription API, se običajno odločate za kompromis. Deepgram vam daje plačevanje po uri, vendar brez plasti AI ali vmesnika za končnega uporabnika. AssemblyAI vam daje API in AI, vendar brez delovnega prostora za vaš tim. Otter vam daje delovni prostor, vendar zaklene API za podjetja in temelji na naročninah. Speak je edini, ki skupaj pošilja vse štiri v enem računu: transcription API, platformo AI, poln spletni in mobilni vmesnik ter plačevanje po porabi brez minimumov in brez roka za potečenje vašega kreditnega stanja.
Plačaj po porabi. Nobena naročnina ni potrebna.
Transkripcija se obračuna na sekundo na osnovi kredita po potrebi, in AI Meeting Assistant deluje po enaki stopnji kreditov. AI Chat se obračuna v kreditih na osnovi porabe. Oglejte si stran s cenami za trenutne cene. Svoje kreditno stanje dopoljnjujte, kadar želite, v poljubnem znesku. Krediti nikoli ne potečejo. Ni pogodbenih obveznosti, nobenih mesečnih minimumov in nobene potrebe po kreditni kartici za pridobitev ključa API in začetek testiranja.
Same rates whether you call the API, use the CLI, the MCP server, or upload through the dashboard. One balance, every surface.
Three lines to your first transcript.
Authenticate, upload, get the transcript back. The API, CLI, and MCP server all hit the same endpoints and pull from the same credit balance.
curl https://api.speakai.co/v1/media/upload
-H "x-speakai-key: $SPEAK_API_KEY"
-H "Content-Type: application/json"
-d '{
"name": "Interview",
"url": "https://example.com/interview.mp3",
"mediaType": "audio",
"sourceLanguage": "en-US"
}'
curl example. Full SDKs and reference at docs.speakai.co.
Connect any AI client in under a minute.
Speak MCP server izpostavi 83 orodij vsakemu MCP-zmožnemu AI odjemalcu. Trije načini povezovanja, odvisno od vašega tima in orodij. Enako kreditno stanje plačevanja po porabi, brez ločenega obračunavanja.
One-Click Connect RECOMMENDED
Browser-based OAuth. Click Connect, approve the permissions popup, done. No API key to paste. Works for Claude.ai, ChatGPT, and any client that supports remote MCP with OAuth. Revoke any time at api.speakai.co/v1/oauth/connections.
API Key plus remote URL
Add the remote MCP endpoint https://api.speakai.co/v1/mcp to your client, then paste an API key generated at app.speakai.co/developers/apikeys. Paste-only setup, no local install. Best for Claude Desktop, Cursor, Windsurf, VS Code, Zed.
Developer CLI
Run npx @speakai/mcp-server init in your terminal. Auto-detects your Claude Desktop, Claude Code, or Cursor install and wires it up. Best for self-hosters and engineers who want the server running locally.
Works with the AI clients your team already uses:
83 tools across 10 categories. Everything your AI client can do with your Speak workspace:
Media library
Upload, list, search, tag, favorite, move, delete media across your workspace.
Magic Prompt
Run custom AI prompts across one file or your entire library. Score, classify, extract.
Iskanje
Full-text search across every transcript, with filters by tag, folder, date, speaker.
Mape
Create folders, move media, manage shared library structure for your team.
Recorders
Create branded recorder URLs, send to respondents, pull in submissions automatically.
Odlomki
Extract verbatim clips from transcripts, export with captions, share or embed.
Meeting bot
Schedule the AI Meeting Assistant for Zoom, Teams, Meet, Webex, and Outlook events.
Avtomatizacije
List, create, toggle, and update workspace automations that run on every new media.
Text notes
Create and update text-only documents alongside audio and video transcripts.
Embed players
Generate public or private embed URLs for transcripts, clips, and analyses.
Prefer no code at all? The Speak Zapier app exposes 5,000+ integrations. Trigger on a new Speak transcript, action on Slack, Notion, HubSpot, Salesforce, Google Sheets, and more. Browse the Speak Zapier app →
How Speak compares.
Trg transcription API z plačevanjem po porabi ima tri resne igralce leta 2026: AssemblyAI, Deepgram in Speak. Otter zaokroži kategorijo delovnega prostora. Speak je edini, ki skupaj pošilja vse štiri sloje (API + AI + UI delovnega prostora + PAYG) v enem računu.
All four layers
- ✓Transcription API
- ✓Cene plačevanja po porabi
- ✓AI Chat over transcripts
- ✓End-user workspace UI
- ✓MCP server (83 tools)
AssemblyAI
API plus AI, no workspace
- ✓Transcription API
- ✓Cene plačevanja po porabi
- ✓AI layer (LeMUR / Claude)
- ✗End-user workspace UI
- ✗MCP server
Deepgram
API plus PAYG, no AI or UI
- ✓Transcription API
- ✓Cene plačevanja po porabi
- ✗AI Chat / analysis layer
- ✗End-user workspace UI
- ✗MCP server
Vidra
Workspace UI, no PAYG API
- ✗API (Enterprise only)
- ✗Plačilo po porabi (samo naročnina)
- ~AI layer (limited)
- ✓End-user workspace UI
- ✗MCP server
Speak je edina platforma, ki povezuje cene blizu API-ja s polnim AI delovnim prostorom. AssemblyAI vam daje API. Otter vam daje UI. Deepgram vam daje plačevanje po porabi. Speak vam daje vse tri, plus AI Chat, MCP in CLI.
Everything in one account.
One API key, one credit balance. Use any surface, any time.
Transcription API
Več kot 100 jezikov, diarizacija govorcev in časovni žigi na ravni besed. REST in webhooks. Obračunavanje po sekundi na kreditnem stanju plačevanja po porabi.
AI Chat over your transcripts
Ask questions across one file or your entire library. Usage-based pricing with model routing handled for you. No separate AI subscription required.
MCP server
83 tools for Claude, Cursor, Windsurf, and any MCP-aware client. Install with npm install and you’re done. Same pay-as-you-go credit balance.
CLI
26 commands to transcribe, search, export, and analyze from your terminal. MIT licensed. Works with the same API key and the same credit balance.
Built for usage that flexes.
No credit card to start.
Sign up, get an API key, run your first call. Pay only when you add credits. The 7-day trial includes full API access and the MCP server at no charge.
Credits never expire.
Dopoljnjujte $10 ali $1.000. Kreditno stanje plačevanja po porabi ostane na vašem računu, dokler ga ne uporabljate. Brez mesečnega porabljenega stanja. Brez datuma potečenja. Vratite se čez šest mesecev in vaši krediti so še vedno tam.
No contracts, no minimums.
Prekličite s preprostim odhodom. Ni pogodbenih obveznosti, nobenih mesečnih minimumov in brez zaklepa. Vaše kreditno stanje plačevanja po porabi ostane na vašem računu, tudi če prenehate uporabljati izdelek.
Teams that build on Speak AI
4.9 na G2
“Speak AI je bil ključen pri spreminjanju načina, kako ravnamo s kvalitativnimi podatki. Natančnost transkripcije je impresivna, vpogledi NLP pa nam prihranijo ure ročne analize.”
Direktor raziskav | Svetovalnica
“Prestopili smo iz Otter.ai in je globina analize na popolnoma drugačni ravni. Ocenjevanje sentimenta, ekstrakcija ključnih besed in odkrivanje tem se izvršijo avtomatično.”
Vodja izdelkov | SaaS podjetje
“Sposobnost iskanja po vseh našimi klici strank in pretrganja specifičnih trenutkov je igra za našo ekipo podpore.”
Vodja CX | Podjetniška tehnologija
Who uses the Speak API
En ključ API, eno kreditno stanje plačevanja po porabi, v vsakem timu, ki gradi na podatkih o glasu in zvoku.
Product engineers
Build transcription directly into your product.
Upload audio via REST, subscribe to the media.analyzed webhook, and get back a structured transcript with speaker labels, word-level timestamps, topics, sentiment, and entities.
Obračunavanje plačevanja po porabi pomeni, da plačate samo za to, kar obdelate.
No subscription tier required, no monthly minimum.
Data and analytics teams
Run AI Chat over your entire transcript library.
Ask questions across thousands of calls, interviews, or recordings.
Obračunano v kreditih na osnovi porabe na istem kreditnem stanju po potrebi.
Use Magic Prompts to extract structured data at scale: MEDDIC scores, objection flags, competitor mentions, NPS signals.
AI engineers and agents
Connect the Speak MCP server to Claude, Cursor, Windsurf, or any MCP-aware client.
83 tools cover transcription, search, export, clip creation, folder management, and more.
Your AI agent can upload audio, wait for analysis, and return structured answers, all through conversation.
Enako kreditno stanje plačevanja po porabi kot REST API.
Prodajne in RevOps ekipe
Auto-transcribe every call your dialer records.
Feed structured data into your CRM on the media.analyzed webhook.
Run Magic Prompts for discovery scoring, competitor extraction, and follow-up action items.
Nobene spremembe nivoja naročnine niso potrebne. Krediti plačevanja po porabi se skalirajo s prostornino vaših klicev.
How a transcript goes from upload to insights
Štiri koraki. Vse na istem pay-as-you-go kreditnem računu.
Naloži
POST your audio or video file URL to https://api.speakai.co/v1/media/upload with your API key in the x-speakai-key header.
Speak accepts public URLs, Twilio recording URLs with embedded auth, and direct file bytes.
Specify source language or let Speak detect it automatically.
Prepisati
Speak queues and processes the recording.
Transcription includes speaker diarization, word-level timestamps, and support for 100+ languages.
A 10-minute call typically completes within 60 seconds.
Obračun je po sekundi na vašem pay-as-you-go kreditnem računu.
Analizirajte
Once the transcript is ready, Speak runs AI analysis automatically: topics, sentiment, named entities, keywords, and any Magic Prompts you have saved for this folder.
The same credit balance covers transcription and analysis.
No separate AI billing required.
React
Speak fires the media.analyzed webhook to your registered endpoint when everything is ready.
Fetch the full transcript and insights from GET /v1/media/insight/:mediaId.
Push structured data to your CRM, trigger downstream automation, or surface insights in your own UI.
Transcription API with AI platform: why they belong together
Večina prepisovalnih API-jev so točkovne rešitve. Dobite končno točko, odgovor in prepis. Kaj naredite s tem prepisom, je povsem vaš problem. Potrebujete ločen klic LLM za povzetke, ločeno bazo podatkov za shranjevanje in iskanje prepisov, ločen uporabniški vmesnik za vaše netehničke kolege in ločeno razmerje obračunavanja za vsako plast, ki jo dodate. Speak je zgrajen na premisi, da te plasti sodijo skupaj v en račun, pod enim pay-as-you-go kreditnim stanjem, brez potrebe po naročnini za začetek.
Kaj pay-as-you-go pomeni za razvijalce API-jev
Plačilo po potrebi na Speak-u pomeni predhodno plačan saldo kreditov, ki ga napolnite v poljubnem znesku. Ni mesečne naročnine, ni minimalnega mesečnega izdatka in ni datuma poteka veljavnosti kreditov, ki jih dodate. Transkripcija se obračuna na sekundo, zato 4-minutni klic stane približno enako malo kot del ure. AI Meeting Assistant in transkripcijski API si delita enako stopnjo kreditov. AI Chat nad vašimi transkripcijami se obračuna v kreditih na osnovi porabe. Vse to crpa iz enega kredita, ne glede na to, katero površino uporabljate: REST API, CLI, MCP strežnik ali nadzorno ploščo.
For developers this means you can onboard without a procurement cycle, test a full pipeline without committing to a subscription tier, and scale usage up or down without renegotiating. If you stop using Speak for two months, your credit balance is waiting for you when you come back.
How the API fits into the broader platform
Speak REST API je osnova. Vsaka druga površina v proizvodu je zgrajena na enih in istih končnih točkah. CLI zavija nalaganje, iskanje, izvoz in analizo končnih točk v 26 terminalnih ukazov. MCP strežnik izpostavlja 83 orodij Claude, Cursor, Windsurf in kateremukoli MCP-osaviščenemu AI odjemalcu. Spletni in mobilni vmesnik omogoča netehničkim kolegom, da uporabljajo isto prepis in AI analizo, ki jo vaša koda sproži prek API-ja. En Speak račun pokriva vse štiri površine. En pay-as-you-go kreditni račun pokriva vso rabo.
Transcription API plus AI Chat: the compound value
Transkripcija vam da tekstovno predstavitev zvoka. AI Chat nad to transkripcijo vam da odgovore. Postavite vprašanje v eni datoteki ali v celotni knjižnici. Identificirajte govorce, izluščite odločitve, poiščite vsak klic, kjer je bila omenjena konkurenca, ali povzemite 50 najdaljših intervjujev v vašem korpusu. AI Chat se obračuna v kreditih na osnovi porabe, usmerjanje modelov je prevzeto za vas, in isti saldo kredita po potrebi ga pokriva. Ni drugega računa, ni drugega ključa API, ni drugega razmerja obračunavanja.
MCP server for Claude and other AI clients
Speak MCP strežnik daje AI asistentom neposreden dostop do vašega Speak delovnega prostora. Claude Desktop, Claude Code, Cursor in Windsurf lahko prepišejo novo avdio, iščejo obstoječe prepise, izvajajo Magic Prompts, izvlečejo segmente govorcev, izvozijo vsebino in še več, vse prek naravnega jezika. Namestite MCP strežnik z npm, prilepite svoj Speak API ključ in katerikoli MCP-osaviščeni odjemalec ima na voljo 83 orodij. Isti pay-as-you-go kreditni račun pokriva vso rabo, sproženo z MCP. Dodatna konfiguracija obračunavanja ni potrebna.
Getting started with the Speak transcription API
Sign up for a free account at app.speakai.co. Open the Developers section of your dashboard to generate an API key. No credit card required. The 7-day trial includes full API access. When you are ready to scale, top up your pay-as-you-go credit balance in any amount. Credits never expire. Full API reference, SDK guides, and webhook documentation are at docs.speakai.co.
Webhooks and async analysis
Speak fires a signed webhook when transcription and AI analysis are complete. Register your endpoint via POST /v1/webhook and specify which event types you want. The media.analyzed dogodek se sproži, ko sta prepis in vsa AI spoznanja pripravljena. Uporabite ga za sprožitev podredne avtomatizacije: potiskajte prepise v svoj CRM, sprožajte Slack opozorila, posodabljajte vrstico baze podatkov ali izvajajte prilagojeni Magic Prompt na vsaki novi posnetki. Webhooks so del istega pay-as-you-go računa, istega API ključa, istega kreditnega stanja.
Speaker diarization and multi-language support
The Speak transcription API supports 100+ languages and automatic language detection. You can specify sourceLanguage on upload or let Speak identify the language for you. Speaker diarization labels each turn in a conversation by speaker, making transcripts of interviews, calls, and meetings immediately parseable without manual cleanup. Word-level timestamps are available on every transcript so you can build video chaptering, subtitle files, or searchable moment-in-time interfaces on top of the API response.
Primerjava pay-as-you-go ponudnikov API-jev v letu 2026
Trg prepisovalnih API-jev pay-as-you-go ima v letu 2026 tri smiselne možnosti: AssemblyAI, Deepgram in Speak. AssemblyAI je najmočnejša izbira, če potrebujete samo API-јев potek dela z vgrajenim LLM orodjem (LeMUR), vendar brez delovnega prostora za končne uporabnike. Deepgram ima najnižjo ceno na uro za surove prepise in močno podporo realnega časa, vendar ni sloja AI analize ali vmesnika delovnega prostora. Speak je prava izbira, ko potrebujete prepise in AI Chat in vmesnik delovnega prostora, ki ga lahko uporabljajo vaši netehniški kolegi, vse pod enim pay-as-you-go kreditnim stanjem brez potrebne naročnine. Prazna četrtina v letu 2026 pripada Speak-u: edini prodajalec, ki pošilja vse štiri plasti v en sam račun.
Using the Speak CLI and MCP server from your API key
Your Speak API key works across every surface. The CLI lets you transcribe a local file with one command: speak transcribe interview.mp3. Isti API ključ in isto pay-as-you-go kreditno stanje. MCP strežnik uporablja isti ključ za dostop Claude in Cursor. Nikoli ne potrebujete upravljanja več ključev, več računov obračunavanja ali več nizov poverilnic. En Speak račun, en ključ, en bilans, vsaka površina.
Questions developers ask.
I don’t write code. Is the API for me?
Probably not. If you want to upload media, run AI Chat over your transcripts, share folders with your team, or use the Meeting Assistant, start at speakai.co/pricing/ and pick a workspace plan. The API is for engineers integrating Speak into their own software.
Do I need a subscription to use the API?
Ne. API se izvaja na pay-as-you-go od prvega dne. Dodajte kredite, kadar želite, v kateremkoli znesku. Naročnine obstajajo za ekipe, ki želijo vključene ure in značilnosti ekipe, vendar nikoli niso potrebne za klic API-ja. Pay-as-you-go kreditna stanja delujejo sama s seboj brez priložene naročnine.
How do I get API keys?
Sign up for a free account, open the Developers page in your dashboard, and generate a key. No card required. Everyone with a Speak account can generate API keys.
Which AI clients work with Speak?
Eight today: Claude.ai (web), Claude Desktop, Claude Code, ChatGPT, Cursor, VS Code, Windsurf, and Zed. Anything that supports MCP works. Use One-Click Connect for Claude.ai and ChatGPT, paste the remote MCP URL plus an API key for desktop apps and IDEs, or run npx @speakai/mcp-server init za lokalno nastavitev. Isto 83 orodij in isto pay-as-you-go kreditno stanje na vsakem odjemalcu.
What is the rate?
Transkripcija in AI Meeting Assistant se oba obračunavata na sekundo na osnovi kredita po potrebi, in AI Chat se obračuna v kreditih na osnovi porabe. Enake stopnje veljajo, ali uporabljate API, CLI, MCP strežnik ali nalaganje preko nadzorne plošče. Polna cena na speakai.co/pricing/.
Get your API key in 60 seconds.
No card. No call with sales. No subscription. Sign up, generate a key, make your first call. Pay only when you add credits.
Pridobite svoj API ključ
Create a free account, open the Developers page, and generate an API key. Full pay-as-you-go access from day one. 7-day trial included. No credit card required.
Explore the docs
Celovit vodnik za končno točko nalaganja, dogodke webhook, Magic Prompt API, orodja MCP strežnika in ukaze CLI. Začnite s pay-as-you-go kreditnim stanjem in se od tam povečajte.




