tools
AssemblyAI
AssemblyAI provides APIs for transcribing, understanding, and building applications with spoken audio.

In inglese
AssemblyAI offers speech-to-text APIs for recorded and realtime audio, plus speaker diarization, language detection, prompting, sentiment analysis, entity detection, summaries, redaction, and other speech-understanding features.
Developers use it for voice agents, meeting notetakers, call analytics, medical documentation, dictation, and contact-center tools. It is an API platform rather than a consumer transcription app; usage is billed based on audio processed or tokens used, with some features costing extra.
Features
- Transcribe recorded audio and video with Universal-3.5 Pro or Universal-2
- Transcribe live audio with realtime speech-to-text APIs
- Detect and label multiple speakers with speaker diarization
- Improve recognition with keyterms prompting and natural-language prompting
- Extract sentiment, entities, topics, translations, and summaries
- Apply PII redaction, profanity filtering, and content moderation
- Route transcripts to multiple language models through LLM Gateway
- Run voice agents through a single WebSocket API
Use cases
- Build realtime voice agents for customer support and sales
- Transcribe meetings and generate summaries, chapters, and action items
- Analyze customer calls for sentiment, topics, entities, and compliance
- Create ambient medical documentation and AI scribe workflows
- Add formatted speech input to dictation features
- Provide live coaching and compliance alerts to contact-center agents
Pros
Cons
Latest updates
- New LLM Gateway Models: NVIDIA Nemotron, DeepSeek v4.1 Flash, GLM 5.3, & GLM 5.3 Flash
Four new models are now live in LLM Gateway: NVIDIA's Nemotron models, DeepSeek's v4.1 Flash, and Zhipu AI's GLM 5.3 and GLM 5.3 Flash.
- Four NVIDIA Nemotron Models Now Available on the LLM Gateway
Four new NVIDIA models are now live in LLM Gateway: Nemotron 3 Nano 30B A3B, Nemotron 3 Super 120B A12B, Nemotron Lightning 3.5 30B A3B, and Nemotron Nano 9B v2.
- Gemini 3.8 Flash Now Available on the LLM Gateway
Google's gemini-3.8-flash is now available through the LLM Gateway. It has a 1M-token context window and supports tool calling, structured outputs, and streaming.
- Kimi K3 Now Available on the LLM Gateway
Moonshot AI's kimi-k3 is now available through the LLM Gateway. It supports tool calling, structured outputs, streaming, and the reasoning_effort parameter.
- MiniMax M3 Now Available on the LLM Gateway
MiniMax's minimax-m3 is now available through the LLM Gateway. It supports tool calling, structured outputs, streaming, and the reasoning_effort parameter.
Capabilities
- Text to speech — “Low-latency speech generation built for realtime conversation.” source
- Speech to text — “Transcribes recorded audio and video asynchronously across 99 languages, with support on speaker diarization, PII redaction, and more features.” source
- Many languages — “Transcribes recorded audio and video asynchronously across 99 languages, with support on speaker diarization, PII redaction, and more features.” source
- API — “Build directly against the raw HTTP and WebSocket API for full control over requests and responses.” source
Get it
Security
- SOC 2 Type II — “We maintain a SOC 2 Type 2 report covering security, availability, and confidentiality, audited annually by an independent firm.” source
- SOC 2 — “We maintain a SOC 2 Type 2 report covering security, availability, and confidentiality, audited annually by an independent firm.” source
- Not trained on your data — “Your data is never used to train or improve our models when you opt out.” source
Pricing
- Starting price
- Free
- Prices checked
- 2026-09-25
Free tier
Free
- Up to 185 hours of pre-recorded transcription
- Up to 333 hours of streaming transcription
Pre-recorded Speech-to-Text API — Universal-3.5 Pro
- $0.21 /hr
- Most accurate async speech-to-text model
- Works across 18 languages
- Native code switching
Pre-recorded Speech-to-Text API — Universal-2
- $0.15 /hr
- Supports 99 languages
- Trained on over 12.5 million hours of audio data
Pre-recorded Speech-to-Text API — Custom
Price on request
- Custom rate limits
- Enhanced concurrency
- Enterprise-grade flexibility
Realtime Speech-to-Text API — Universal-3.5 Pro Realtime
- $0.45 /hr
- Supports 18 languages
- Context carryover and conversation memory
- Self-correcting speaker labels and voice isolation
Realtime Speech-to-Text API — Universal-Streaming
- $0.15 /hr
- English-only transcription
- Purpose-built for production voice applications
Realtime Speech-to-Text API — Universal-Streaming Multilingu
- $0.15 /hr
- Supports English, Spanish, German, French, Portuguese, and Italian
Realtime Speech-to-Text API — Custom
Price on request
- Custom rate limits
- Enhanced concurrency
- Enterprise-grade flexibility
Sync Speech-to-Text API — Sync API
- $0.45 /hr
- Process up to 2 minutes per request
- Results in ~134 ms (p50)
- Per-word timing and confidence across 18 languages
Sync Speech-to-Text API — Custom
Price on request
- Custom rate limits
- Enhanced concurrency
- Enterprise-grade flexibility