AssemblyAI Pre-recorded Speech-to-Text API
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.
Find alternatives to AssemblyAI Pre-recorded Speech-to-Text API
What it does
- Speech to text
Used for
- Meeting notes
- Regulatory compliance review
- Clinical documentation
Features 11
- Speaker DiarizationSeparates every voice in a conversation into a speaker-labeled transcript with timestamps.
- Speaker IdentificationReplaces generic speaker labels with real names or roles inferred from the conversation.
- Summarization + ChaptersTurns recordings into concise summaries and timestamped chapters with a headline and gist.
- Sentiment AnalysisClassifies sentiment as positive, neutral or negative per sentence and per speaker.
- Entity DetectionReturns names, dates, account numbers and 50+ other entity types as typed fields with timestamps.
- Topic DetectionClassifies what audio is about against the standard IAB Content Taxonomy categories.
- Automatic Language DetectionDetects the dominant language of an audio file and transcribes it across 99 languages.
- PII RedactionRemoves personally identifiable information from the transcript and bleeps it from the audio.
- Medical ModeAdd-on for clinical-grade transcription with medical terminology recognition.
- Code-Switching TranscriptionDetects and transcribes code-switching in pre-recorded audio, with best results for English plus Spanish or English plus German.
- Term Spelling ControlLets you set how particular words are spelled or formatted in the transcript.
How it compares
-
Deepgram Speech-to-Text
Deepgram's own comparison page is titled as a head-to-head with AssemblyAI.
AssemblyAI vs Deepgram: Is Deepgram the Right Alternative?
Company disclosure · 14 Oct 2026 -
Speech to Text API
Speechmatics' own comparison page is titled as a head-to-head with AssemblyAI.
Speechmatics vs AssemblyAI: Speech-to-Text Comparison (2026)
Company disclosure · 23 Sep 2026 -
Scribe
AssemblyAI Universal-3.5 Pro Mistral Voxtral Mini OpenAI GPT-4o Transcribe Cohere Transcribe ElevenLabs Scribe V2
Official documentation · 13 Oct 2026
Sources
- Pricing
-
Official documentation · 9 Oct 2026
"Pay-as-you-go: $0.15/hr for Universal-2, $0.21/hr for Universal-3.5 Pro, +$0.07/hr for Medical Mode on any base model. Billed per second. Optional Speech Understanding features are priced separately." 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
"Get clean, customizable transcripts in 99 languages with industry-leading accuracy and natural language prompting." The pricing page section adds language detection, formatting, filler words, keyterms prompting, custom spelling and word-level timestamps.
- What it does
- Used for
-
Official documentation · 23 Oct 2026
'AI notetakers Turn recorded meetings into structured summaries with speaker attribution, action items, and searchable timestamps.' (https://www.assemblyai.com/products/speech-to-text) / 'Compliance monitoring Review recorded calls for regulatory exposure with audit-grade transcripts.' (https://www.assemblyai.com/products/speech-to-text) / 'Medical transcription Build medical documentation workflows on models engineered for patient interactions and clinical environments.' (https://www.assemblyai.com/products/speech-to-text)
- Constraints
-
Official documentation · 12 Oct 2026
Derived from the security facts on this page, from the same source.
- Security
-
Official documentation · 12 Oct 2026
Page: 'We maintain a SOC 2 Type 2 report covering security, availability, and confidentiality'. / Page: 'Paid accounts can opt out from the Data Controls page'. / Page: 'Pre-recorded transcription doesn't offer zero retention'. / Page: 'Data under a signed BAA or sent to our EU servers is never used for training'. / Page: 'Data is encrypted in transit with TLS 1.2+ and at rest with AES'.
- Sold within
-
Its own pay-as-you-go section on the pricing page (Universal-3.5 Pro $0.21/hr, Universal-2 $0.15/hr), bought directly from AssemblyAI with no parent offering.
- Name
-
Official documentation · 9 Oct 2026
Page heading: "Pre-recorded Speech-to-Text API".
- URL
-
Official documentation · 9 Oct 2026
The product's own page, one of three transcription products in AssemblyAI's menu (pre-recorded, realtime, sync).
- Interfaces
-
Official documentation · 19 Oct 2026
Product page FAQ "How do I get started with AssemblyAI's API?": "Sign up and get your API key in the Dashboard. Install an SDK (e.g., JavaScript or Python)." Earlier PyPI listing (https://pypi.org/project/assemblyai/) supports sdk.
- Modalities
-
Official documentation · 1 Oct 2026
Page: 'Pre-recorded Speech-to-Text API / 2 million hours of audio processed every day'.
Also from AssemblyAI
-
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 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-speech-to-text.