AssemblyAI Voice Agent API
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.
Find alternatives to AssemblyAI Voice Agent API
What it does
- Voice agent
- Speech to text
- Text to speech
Features 5
- Turn detectionKnows when the user is done talking versus pausing, and stops listening when interrupted.
- Natural voice generationPurpose-built text-to-speech voices tuned for real-time conversation.
- Session resumptionReconnect within 30 seconds if the WebSocket drops and the conversation continues with context preserved.
- Accurate entity transcriptionTranscribes email addresses, phone numbers and entity names correctly so the LLM responds to what was said.
- Six-language supportSupports English, Spanish, French, German, Italian and Portuguese.
How it compares
-
Deepgram Voice Agent API
Compare APIs Model AssemblyAI Voice Agent API OpenAI Realtime API Deepgram Voice Agent API
Official documentation · 13 Oct 2026
Sources
- Pricing
-
Official documentation · 9 Oct 2026
"Voice Agent API is a single flat hourly rate of $4.50/hr that covers speech-to-text, LLM reasoning, and voice generation on one connection. You pay per second of session duration." Pricing page: "Billed per second on connected conversation time." Docs: "Any LLM Gateway calls made by the agent are billed separately". Telephony through the customer's own Twilio account is included with no markup. The one-time new-account 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") is not a recurring free tier.
- Description
-
Official documentation · 9 Oct 2026
"Voice Agent API is a single connection that handles speech-to-text, LLM routing, and voice generation for production voice agents."
- What it does
-
The pricing page lists the stack as Universal-3.6 Pro Realtime, the Voice Agent LLM and Voice Agent TTS, all included.
- Sold within
-
Its own pricing section: "Every feature is included in the $4.50/hr rate. There are no per-layer add-ons, concurrency fees, or per-agent subscriptions."
- Name
-
Official documentation · 9 Oct 2026
Page heading: "Voice Agent API" ("Renamed to Voice Agent API at GA in April 2026", models list, formerly Speech-to-Speech API).
- URL
-
Official documentation · 9 Oct 2026
The product's own page.
- Deployment
-
"Managed orchestration and hosting for production voice agents."
- Interfaces
-
Official documentation · 9 Oct 2026
"Standard JSON API, no SDKs"; the SDK docs say "Voice Agent and LLM Gateway are not currently supported in the AssemblyAI SDK."
- Modalities
-
Official documentation · 12 Oct 2026
Page: 'Voice Agent API is a single connection that handles speech-to-text, LLM routing, and voice generation for production voice agents'.
- Intended for
-
Official documentation · 9 Oct 2026
An API for developers building voice agents.
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 Realtime Speech-to-Text API API service
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.
-
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-voice-agent-api.