AssemblyAI Realtime Speech-to-Text API
Live transcription API: audio streamed over a WebSocket comes back as text within a few hundred milliseconds, with endpointing for voice agents, sold by the hour of session time and also offered self-hosted.
Find alternatives to AssemblyAI Realtime Speech-to-Text API
What it does
- Speech to text
Features 6
- Partial and final transcriptsStreams partial and final transcripts with roughly 150 ms P50 latency.
- Automatic language detectionDetects language automatically across 32 supported languages on the flagship realtime model.
- Keyterm promptingSupports keyterm prompting of up to roughly 100 words on all realtime models.
- Speaker diarizationSeparates 10+ speakers in streaming audio.
- Medical ModeAdd-on for clinical-grade streaming accuracy and medical terminology recognition.
- Code-switchingHandles speakers moving between languages mid-conversation on supported models.
Sources
- Pricing
-
Pricing page, Realtime Speech-to-Text API section, pay as you go: Universal-3.6 Pro Realtime $0.45/hr, Universal-Streaming $0.15/hr, Universal-Streaming Multilingual $0.15/hr. Docs: "Streaming Speech-to-Text is billed on the total duration that your WebSocket connection stays open, not on the amount of audio you send." A custom tier is "Contact us". New accounts get a one-time credit ("New accounts receive $50 in free credits for Pre-recorded STT, Real-time STT, Voice Agent API, Speech Understanding, and Guardrails. Credits do not expire", docs billing page), which is not a recurring free tier.
- Description
-
Official documentation · 9 Oct 2026
"The Realtime Speech-to-Text API transcribes live audio as it's spoken. You send audio over a secure WebSocket to the API, which returns transcripts within a few hundred milliseconds (~300 ms P50)."
- What it does
-
Official documentation · 9 Oct 2026
"transcribes live audio as it's spoken".
- Sold within
-
Official documentation · 9 Oct 2026
"Production-grade transcription for voice agents, available standalone or through our Voice Agent API." Its own rates: "Universal Streaming is $0.15 per hour. Universal-3.6 Pro Realtime is $0.45 per hour. Billing is based on total session duration."
- Name
-
Official documentation · 9 Oct 2026
Page heading, title and product menu: "Realtime Speech-to-Text API".
- URL
-
Official documentation · 9 Oct 2026
The product's own page, separate from the pre-recorded and sync APIs in the same menu.
- Deployment
-
Official documentation · 9 Oct 2026
Hosted API, and "The AssemblyAI Self-Hosted Streaming Solution provides a secure, low-latency real-time transcription service that can be deployed within your own infrastructure." Self-hosting is sales-led: "Self-hosted streaming requires an upfront commercial commitment of $20,000."
- Interfaces
-
Official documentation · 9 Oct 2026
"connect to the WebSocket endpoint, set your sample rate, stream audio chunks, and handle transcript events. Our SDKs for Python and JavaScript make it a few lines of code."
- Modalities
-
Official documentation · 12 Oct 2026
Page: 'Real-time transcription powers every application where you stream audio'.
- Intended for
-
Official documentation · 9 Oct 2026
An API for developers building voice products.
Also from AssemblyAI
-
AssemblyAI Pre-recorded Speech-to-Text API API service
Speech-to-text API for recorded audio and video files: transcripts in 99 languages with speaker diarization, language detection, word-level timestamps and keyterm prompting, billed per second of audio.
-
AssemblyAI Voice Agent API API service
One connection that runs a production voice agent end to end: speech recognition, a conversational language model, voice generation, turn detection, interruptions and tool calls, at one flat hourly rate.
-
AssemblyAI Speech Understanding API API service
Add-on models switched on in a transcription request that turn recorded audio into structured output: speaker labels, sentiment, entities, topics, key phrases, summaries, translation and custom formatting, each priced per audio hour.
-
AssemblyAI LLM Gateway API service
OpenAI-compatible API that routes requests to GPT, Claude, Gemini, Qwen and other hosted models with automatic fallbacks, at the providers' own token prices with no markup, beside AssemblyAI's speech APIs.
-
AssemblyAI Guardrails API service
Safety add-ons for transcription requests: profanity filtering, content moderation and redaction of personal data in the transcript text and in the audio itself, each toggled per request.
-
Sync Speech-to-Text API API service
Returns a transcript of a short audio clip in a synchronous API response.
-
Dictation API API service
Converts spoken audio into text with a cleanup pass and an accompanying verbatim transcript.
-
Blurt Application
Converts speech into text wherever the user is typing.
Open AssemblyAI in the directory
Something wrong here? Send a correction — quote this product id: assemblyai-streaming-speech-to-text.