Empathic Voice Interface (EVI)
Empathic Voice Interface (EVI) is Hume's real-time speech-to-speech voice AI API, described in Hume's docs as 'an advanced, real-time emotionally intelligent voice AI.' The product page markets it as a way to 'Build voice-first AI experiences that understand and respond to human emotions' and states it 'works seamlessly with Claude, GPT, Gemini, Grok, Kimi K2, Llama, and more' - layering voice on top of third-party language models rather than supplying its own. It is billed per conversation minute on Hume's public plans. Hume's changelog notice of 2 October 2026 says it is sunsetting the TTS and EVI APIs: access ends on 13 November 2026 at 12:01 a.m. EST, and both APIs remain fully supported until then.
Find alternatives to Empathic Voice Interface (EVI)
What it does
- Voice agent
- Text to speech
Features 5
- Transcription (ASR)Returns a full transcript of the conversation with Hume's expression measures tied to each sentence.
- End-of-turn detection from toneUses the user's tone of voice to decide when to respond without interrupting.
- InterruptibilityStops rapidly when users interject and resumes with the right context.
- Voice response (TTS)Streamed speech generation via Hume's speech-language model.
- EVI PlaygroundA browser playground in the Hume platform for trying EVI.
Sources
- Pricing
-
'EVI 3' and 'EVI 4 mini' listed under Speech-to-Speech; per-minute rates '$0.07/minute' (Creator) to '$0.04/minute' (Business).
- Description
-
Official documentation · 5 Sep 2026
Page title 'Empathic Voice Interface (EVI) - AI Conversations with Emotional Intelligence'; 'Build voice-first AI experiences that understand and respond to human emotions'; 'works seamlessly with Claude, GPT, Gemini, Grok, Kimi K2, Llama, and more'.
- Constraints
-
Official documentation · 2 Oct 2026
Derived from the security facts on this page, from the same source.
- Security
-
Official documentation · 2 Oct 2026
EVI API only (dev.hume.ai privacy page). Same page conflicts on training: EVI section says anonymized data used by default with opt-out, FAQ says API data not used to train, so trains left unknown. BAA/DPA stated as requestable from Hume.
- Sold within
-
hume.ai/pricing (already cited pricing-page elsewhere on this record); its own metered line item, bought directly on Hume's public plans.
- Name
-
Official documentation · 5 Sep 2026
Docs navigation entry 'Empathic Voice Interface (EVI)' - 'an advanced, real-time emotionally intelligent voice AI'.
- Interfaces
-
Official documentation · 14 Oct 2026
Page: 'Develop server-side or frontend applications using our TypeScript SDK'.
- Modalities
-
Official documentation · 1 Oct 2026
Page: 'Build voice-first AI experiences that understand and respond to human emotions / streaming audio output'.
- Intended for
-
"Build voice experiences in minutes" with full SDK support; "Built for business" with SOC 2 Type II, HIPAA compliance, custom SLAs and volume pricing
- Discontinued
-
Company disclosure · 4 Nov 2026
Same changelog entry, read 2026-11-04: "Access ends November 13, 2026 at 12:01 a.m. EST." A future date, not yet reached: access continues until then.
Also from Hume AI
-
Kairos Platform Platform
Evaluation platform for voice agents: it builds evaluation suites from real-world use cases, simulates agent-to-agent and human-to-agent conversations against any voice model, and tracks regressions over time.
-
Octave TTS API service
Octave TTS is Hume's text-to-speech API, which Hume's documentation calls 'the first text-to-speech system built on LLM intelligence.' The marketing page positions it as 'Text-to-speech with emotional intelligence' that generates 'expressive, natural-sounding speech that conveys the full range of human emotion,' with SDKs for Python, TypeScript, .NET and Swift and streaming audio output. It is billed by characters on Hume's public self-serve plans. Hume's changelog notice of 2 October 2026 says it is sunsetting the TTS and EVI APIs: access ends on 13 November 2026 at 12:01 a.m. EST, and both APIs remain fully supported until then.
-
Creator Studio Application
Creator Studio is Hume's web application, hosted at app.hume.ai, for turning written documents into narrated audio: 'From document to audio, effortlessly. Import your content, assign voices, add acting directions, and export production-ready audio.' Hume targets it at creators producing audiobooks, videos, podcasts, documentaries, e-learning courses and corporate training that need multi-voice narration with emotional direction.
-
Expression Measurement API API service
The Expression Measurement API measures emotional and vocal expression in speech, marketed as 'Measure expression in voice, offline or in real time.' Hume describes two endpoints on the one page: 'The Tagger API returns 600+ expression and voice dimensions from any audio, at scale. The Prosody API delivers real-time emotional expressions during live conversations.' Measured dimensions include emotion categories, speaking styles, vocal qualities such as pace, warmth and hesitation, and expression intensity with confidence scores.
-
Human Feedback API API service
The Human Feedback API sells human evaluation of voice and conversational AI as an API call, marketed as 'One API call. Real human ratings.' and 'Plug human evaluation into your pipeline. Audio in, structured results out.' It supports three study types - live conversations with AI models, single-sample audio ratings with custom questions, and side-by-side A/B comparisons - with Hume handling participant recruitment, quality control and fraud detection. Hume states it powers 'evaluation for Hume's own frontier voice models.'
-
Data Solutions Data service
Data Solutions is Hume's licensed AI training-data offering, headlined 'Voice Training Data Built by Researchers, for Researchers' and described as 'Datasets for creating realistic voices across global languages, powering our own state-of-the-art models, and now available to power yours.' The catalogue spans voice datasets covering 50+ languages, 48+ emotions and 600+ voice descriptors, plus expression and multimodal datasets for facial expression, vocal bursts, speech prosody and text emotion. Hume also sells custom data collection with defined speakers and recording conditions, and API access for programmatic data refresh and generation.
-
Prism EQ Pipeline Infrastructure service
Prism EQ Pipeline transforms audio into searchable inputs with transcription and labels for speaker, language, and expression.
-
User Testing API API service
User Testing API runs tests of voice models with human participants.
Something wrong here? Send a correction — quote this product id: hume-ai-evi.