Shunya LabsShunya LabsPlayground

Horizon · Spanish

Spanish Speech to Text

Convert spoken Spanish into accurate, structured text for voice agents, customer conversations, meetings, media, contact centers, captions, analytics, and real-time AI applications. Use Shunya Horizon Universal to transcribe Spanish speech with streaming and batch recognition, speaker labels, timestamps, multilingual understanding, and optional conversation intelligence.

204+ languages supported3.10% composite WER (global)Sub-500ms streaming latency#1 OpenASR composite
Transcript · Spanish

Hola, llamo porque hice el pago ayer, pero todavía no he recibido la confirmación.

Speaker diarization · Horizon Universal
Language · SpanishModel · Horizon UniversalStreaming · Real-timelanguage_code: es

Spanish STT

Spanish Speech In. Structured Text Out.

Spanish is spoken across many countries, accents, industries, and conversational environments. Real speech may contain regional pronunciation, fast conversation, English terminology, names and addresses, phone-line audio, background noise, multiple speakers, interruptions, and technical vocabulary. Horizon Universal includes Spanish in Shunya's global speech-recognition coverage.

204+

Languages supported across the current Horizon platform

3.10%

Composite WER across Shunya's 8-benchmark OpenASR evaluation

Sub-500ms

Streaming transcription across the current product platform

#1

OpenASR composite positioning published by Shunya

CapabilityHorizon · Spanish Speech to Text
Spanish Language Recognition
Batch Transcription
Real-time Streaming
Automatic Language Detection
Speaker Diarization
Speaker Identification
Word-level Timestamps
Confidence Scores
Multilingual Recognition
Code-switching
Intent & Sentiment
Summarisation
Private Deployment Options

Spanish model: Use Horizon Universal for Spanish and other global languages.

Try it yourself

Test the Spanish your Users Actually Speak

A clean prepared recording cannot tell you how ASR will perform on your customer calls,regional accents, names, addresses, product terminology, or noisy conversations.

Global speech recognition

Spanish Is Part of a Larger Global ASR System

Horizon Universal is Shunya's model for broad multilingual speech recognition, spanning 204+ languages and dialects worldwide. Spanish appears explicitly inShunya's international-language documentation alongside languages such as:

EnglishJapaneseChineseArabicGermanFrenchPortugueseRussianKoreanTurkishVietnameseIndonesian

One API

Spanish today. Another global language tomorrow.

The application does not need a completely different ASR architecture for each language.

Benchmarks

Global Benchmark Results, and How toTest Your Spanish

Shunya publishes 3.10% composite WER across 8 OpenASR benchmarks. That evaluation includes datasets such as:

3.10%

Composite WER across 8 OpenASR benchmarks

LibriSpeechSPGISpeechTED-LIUMAMIVoxPopuliGigaSpeechEarnings22

Important: These benchmarks show Horizon's overall performance. They are not a Spanish-only benchmark: Shunya has not yet published a Spanish-specific word error rate.

Spanish support: Spanish is supported by Horizon Universal. The figures above are composite results across benchmarks, not a Spanish score.

The right test: Upload the Spanish conversations your application actually receives.

Test Horizon on your Spanish audio

Spanish accents

Spanish Doesn't Sound the Same Everywhere

Spanish is spoken across many regions. Pronunciation, rhythm, vocabulary, and conversational style can vary across:

SpainMexicoArgentinaColombiaChilePeruCentral AmericaThe CaribbeanThe United StatesOther Spanish-speaking communities

Real-world variation

One speaker may say computadora while another may prefer ordenador. A customer may speak slowly and formally. Another may speak quickly and conversationally.

ASR needs to handle

  • Accent variation
  • Speaking speed
  • Vocabulary variation
  • Names
  • Regional expressions
  • Phone audio
  • Background noise

Global model

Horizon Universal is the appropriate Shunya model path for Spanish speech.

Real-world Spanish

People Don't Speak Like Textbooks

Production Spanish audio can include pauses, restarts, fillers, fast speech, critical names and numbers, and noisy environments.

Pauses

Quería saber... bueno, si mi pedido ya salió.

Restarts

Necesito cambiar... en realidad, quiero cancelar mi pedido.

Fillers

Bueno... Pues... Eh...

Fast speech

Speakers may join words together during natural conversation.

Names and places

Customer names, addresses, cities, and brands may be the most important words in the transcript.

Numbers

Phone numbers, order IDs, amounts, dates, and times.

Background noise

Contact centers, stores, traffic, homes, and public places.

Speech recognition needs to work on conversation, not just carefully read Spanish.

Spanish + English

Because Real Conversations Can Switch Languages

Spanish-speaking users often include English terminology, especially in:

TechnologyCustomer supportRetailBankingTravelSoftwareTelecom

Payment conversation

Mi payment ya fue procesado pero todavía no recibí el confirmation email.

Support conversation

La app abre, pero el login button no funciona.

Product conversation

Quiero cambiar mi subscription al Premium plan.

One conversation

Spanish + EnglishHorizon Code-SwitchOne continuous transcript

Shunya's Horizon Code-Switch model is built for multilingual speech without requiring separate language detection and model handoffs.

Important: Shunya publicly lists many multilingual combinations, but not every possible pair is available individually. For production Spanish-English code-switching, test your real audio and confirm the appropriate Horizon Code-Switch routing available in your deployment.

Real-time Spanish transcription

See Spanish Text while the Speaker Is Still Talking

Some applications need the transcript immediately. Horizon supports streaming speech recognition through WebSocket connections.

Live audio flow

Microphone / phone / app streamHorizon streamingPartial transcriptFinal transcript

Text appears while speech continues. Segments are finalised as the conversation progresses. Use batch transcription when the complete recording is already available.

Batch vs streaming

Transcribe Now or After the Conversation

Streaming

For live Spanish speech

  • Spanish voice agents
  • Live captions
  • Customer support
  • Agent assist
  • Interactive assistants
  • Real-time applications
  • IVR

Batch

For completed Spanish recordings

  • Meetings
  • Interviews
  • Calls
  • Podcasts
  • Videos
  • Research
  • Post-call analytics
RequirementStreamingBatch
Live Spanish speech
Recorded audio
Partial transcripts
Complete transcript
Voice agents
Post-processing
WebSocket
HTTP API

Who said what

Keep Speakers Attached to their Words

A Spanish customer call may look like this: SPEAKER_00 Hola, quiero revisar el estado de mi pedido.SPEAKER_01 Claro. ¿Puede darme el número del pedido? SPEAKER_00 Sí, es 48217.

Without diarization

One block of text

Hola, quiero revisar el estado de mi pedido. Claro. ¿Puede darme el número del pedido? Sí, es 48217.

With diarization

Speaker-separated segments

SPEAKER_00 Hola, quiero revisar el estado de mi pedido.

SPEAKER_01 Claro. ¿Puede darme el número del pedido?

SPEAKER_00 Sí, es 48217.

Useful for

Customer calls

Meetings

Interviews

Podcasts

Research

Sales conversations

Support analytics

Speaker identification

Go Beyond "Speaker 01"

Diarization answers:
Who spoke when?

Speaker identification can resolve known registered voices where configured.

Before

SPEAKER_01

Voy a revisar su cuenta.

After

Agent Maria

Voy a revisar su cuenta.

Workflow

Register a clean voice profile.Enable diarization.Enable speaker identification.Resolve matching speakers.

Unknown speakers can remain anonymous labels.

Word-level timestamps

Know Exactly when Each Word Was Spoken

Verbose Horizon output can include start time, end time, and confidence score per word. Use timestamps for captions, search, call review, meeting playback, media editing, transcript highlighting, subtitles, and training data.

WordStartEndConfidence
gracias1.14s1.48s0.98
por1.49s1.60s0.99
llamar1.61s1.98s0.97

Search workflow: "cancelar pedido" → find transcript match → jump directly to the moment in the audio.

From Spanish transcript to intelligence

Sometimes the Words Are Only the First Layer

For supported batch workflows, Shunya's intelligence layer can enrich a Spanish transcript.

Speaker diarization

Who spoke when?

Speaker identification

Which registered speaker was talking?

Intent

What does the speaker want?

Sentiment

Is the interaction positive, neutral, or negative?

Emotion

What dominant emotion appears in each segment?

Summary

What happened in the conversation?

Keyterms

Normalise important domain vocabulary.

Word timestamps

Connect text back to the audio.

Redaction

Mask configured sensitive terms.

Profanity masking

Mask profane transcript content.

Enrichment pipeline

Spanish audioTranscriptSpeakers + timingIntelligenceCRM / analytics / search / LLM

Spanish voice agents

Spanish STT as the Listening Layer

A Spanish voice agent first needs to understand what the user says. Horizon becomes the listening layer of the Spanish conversational AI stack.

STT → LLM → TTS

User speaks: Quiero saber cuándo llegará mi pedido.Horizon transcribes the Spanish speechLLM / agent understands and generates a responseRadiance generates spoken SpanishUser hears: Tu pedido llegará mañana.

Real-world use cases

Spanish Speech to Text Wherever Spoken Language Needsto Become Usable Data

Voice Agents

Convert Spanish customer speech into machine-readable text in real time.

Contact Centers

Transcribe Spanish calls for quality, analytics, summaries, search, and agent workflows.

Meetings

Create searchable Spanish transcripts with speaker separation and timing.

Media

Transcribe Spanish podcasts, interviews, webinars, videos, and broadcasts.

Travel & Hospitality

Capture spoken Spanish interactions for multilingual customer-service workflows.

Retail

Understand Spanish customer questions in stores, kiosks, and voice interfaces.

Banking & Financial Services

Transcribe Spanish customer-service conversations and account-related interactions.

Education

Convert Spanish lessons, discussions, and lectures into searchable text.

Research

Transcribe Spanish interviews, surveys, and qualitative research sessions.

Accessibility

Provide text output for spoken Spanish content.

Audio & video input

Transcribe the Formats your Workflow Already Creates

Horizon batch transcription accepts common audio formats. Shunya's batch workflow also supports common video formats by extracting the audio track first.

Audio formats

Supported uploads

  • WAV
  • MP3
  • M4A
  • OGG
  • FLAC
  • WebM

Video formats

Audio track extracted

  • MP4
  • MOV
  • MKV
  • AVI
  • WebM

Video workflow

MP4 / MOV / MKV / AVI / WebMAudio trackHorizonSpanish transcript

Spanish transcription works across calls, interviews, meetings, media files, and video content.

Developers

Add Spanish Transcription to your Application

Use Horizon Universal for Spanish. Model: horizon-universal. Language: Spanish (es). You can also leave language detection on automatic when the language is not known in advance. When you already know the audio is Spanish, explicitly locking the language can reduce ambiguity, especially for short clips. Use GET /languages for the current supported language names, ISO codes, and scripts.

batch-transcription.json

{
  "model": "horizon-universal",
  "language_code": "es",
  "file": "spanish-call.wav"
}

Input

Spanish audio

Audio file, URL, or live stream.

Model

horizon-universal

Language code es.

Configure

Transcript features

  • Speaker diarization
  • Speaker identification
  • Word timestamps
  • Emotion
  • Intent
  • Sentiment
  • Summary
  • Redaction

Output

Structured JSON

  • Spanish transcript
  • Timing
  • Language information
  • Speakers
  • Enabled intelligence fields

Example logic

spanish-call.wavhorizon-universalesSpanish transcript
Explore the Speech to Text API

Choose the right model

The Right ASR Model Depends on the Conversation

Spanish-first speech

Horizon Universal

Use for ordinary Spanish transcription and broader global-language audio.

Best for:

  • Spanish calls
  • Meetings
  • Media
  • Customer service

Mixed-language speech

Horizon Code-Switch

Use where conversations naturally switch languages and the relevant combination is supported by the deployment.

Best for:

  • Spanish + English calls
  • Voice agents
  • Support
  • Product conversations

Clinical speech

Horizon Medical

Use for healthcare-oriented transcription when the conversation requires the medical model and its supported language workflow.

Best for:

  • Clinical conversation

Model follows the audio

AudioModel
SpanishHorizon Universal
Mixed multilingual speechHorizon Code-Switch
Specialised clinical use caseAppropriate domain model

Built for production

Beyond the Microphone Demo

A clean Spanish sample can make almost any ASR system look useful. Production audio is harder.Teams need streaming, multilingual coverage, speakers, timestamps, APIs, intelligence,deployment options, and the ability to handle the audio users actually produce.

RequirementHorizon
Spanish Speech to Text
Horizon Universal
Spanish Language Code (es)
Batch Transcription
Streaming Transcription
Automatic Detection
Speaker Diarization
Speaker Identification
Word-level Timestamps
Confidence Scores
Multilingual Recognition
Code-switching Platform
Intent Detection
Sentiment Analysis
Emotion Detection
Summarisation
Redaction
API Integration
Enterprise Deployment

Production output

Spanish speechHorizonStructured textSearch · analytics · CRM · LLM · voice agent · knowledge base

Questions

Frequently Asked Questions

What is Spanish Speech to Text?

Spanish Speech to Text uses automatic speech recognition to convert spoken Spanish into written text.

Does Shunya support Spanish Speech to Text?

Yes. Spanish is explicitly included in Shunya's international-language speech-recognition coverage.

Which model should I use for Spanish?

Use Horizon Universal for Spanish and other global languages.

What is the Spanish language code?

The standard ISO 639-1 language code is es. Shunya's API supports language hints and also provides GET /languages for the current routable language list.

Can Shunya detect Spanish automatically?

Yes. Horizon supports automatic language detection.

How many languages does Horizon support?

Horizon Universal spans 204+ languages and dialects. For exact deployable coverage, use the live GET /languages endpoint or the language list exposed by your deployment.

Does Shunya publish a Spanish-specific WER?

Not yet. Shunya publishes a 3.10% composite WER across 8 OpenASR benchmarks; it is not a Spanish-only figure.

Can Shunya transcribe Spanish in real time?

Yes. Horizon supports WebSocket streaming transcription.

Can Shunya distinguish different Spanish speakers?

Yes. Speaker diarization can separate participants into speaker-labelled transcript segments.

Can known speakers be identified?

Yes. Registered voice profiles can be combined with speaker identification where configured.

Can I get Spanish word timestamps?

Yes. Verbose transcript output can contain word-level start time, end time, and confidence information.

Can Shunya summarise Spanish recordings?

Shunya's batch intelligence layer supports summarisation and other transcript enrichment. Test the feature on your Spanish production content to confirm the quality needed for your workflow.

Can Spanish transcripts include intent and sentiment?

Shunya's intelligence layer includes intent, sentiment, emotion, summary, and other optional enrichment features.

Can Spanish speech include English words?

Yes. Real Spanish frequently contains English terminology. For heavily code-switched conversations, use the Horizon Code-Switch model where the relevant combination is supported and test your own audio.

Can Shunya transcribe Spanish video?

Yes. Shunya's batch transcription workflow accepts supported video containers, extracts the audio track, and transcribes the speech.

Is Spanish Speech to Text available through an API?

Yes. Horizon provides HTTP batch transcription and WebSocket streaming.

Get started

Turn Spanish Speech into Text

Don't judge Spanish ASR from our prepared recording. Test yours. Try a customer call, regional accent,Spanish-English conversation, interview, meeting, podcast, video, voice note, or noisy real-worldrecording. See the transcript, speakers, timestamps, and structured output for yourself.