Alternatives to Eleven Realtime
Compare Eleven Realtime alternatives for your business or organization using the curated list below. SourceForge ranks the best alternatives to Eleven Realtime in 2026. Compare features, ratings, user reviews, pricing, and more from Eleven Realtime competitors and alternatives in order to make an informed decision for your business.
-
1
GPT-Realtime-2.1
OpenAI
GPT-Realtime-2.1 is OpenAI’s reasoning model with tool use for low-latency voice agents and complex speech-to-speech workflows. It updates GPT-Realtime-2 with improved alphanumeric recognition, silence and noise handling, and interruption behavior, helping applications understand spoken code, manage imperfect audio, and respond more naturally when users pause or talk over the agent. Developers can configure reasoning effort to balance deeper thinking against latency and output usage, while strong instruction following helps the model stay aligned with a defined role, tone, and workflow. It accepts and produces both audio and text, can take images as input, and supports function calling so an agent can retrieve information or perform actions during a conversation. The model has a 128,000-token context window, supports up to 32,000 output tokens, and includes reasoning-token support for extended interactions.Starting Price: $0.40 per cached input -
2
Inworld Realtime STT
Inworld
Inworld Realtime STT is a realtime streaming STT API that understands users beyond their words. It combines low-latency speech recognition with voice profiling, extracting emotion, vocal style, accent, age, and pitch directly from raw audio so downstream LLMs and TTS systems can respond with more adaptive, expressive behavior. Developers can stream audio in real time, transcribe complete files, or extract voice profile signals through one unified API, with realtime bidirectional streaming over WebSocket, synchronous transcription for full audio files, voice profile signals on every streaming chunk, and multi-provider support through a single model ID. Every audio chunk can produce a realtime profile of the speaker with confidence scores, giving LLMs structured context such as whether a user sounds sad, frustrated, soft, high-pitched, or calm.Starting Price: Free -
3
Dessa
Block
Dessa is Block's speech-to-speech artificial intelligence model for conversational voice research and applications. It takes audio input and produces audio output directly, without converting speech into text as an intermediate step. Trained from scratch on human conversation rather than text, the model supports full-duplex interaction, listening and speaking at the same time, and runs locally on a MacBook Pro with an M4 Max chip or better. It captures conversational cues such as emotion, sarcasm, laughter, pauses, and turn-taking that can be lost in text-based pipelines. Dessa is intended for AI safety researchers and developers studying voice-model behavior, privacy, and real-time interaction. It is a speech model for research and development, not a general-purpose business application or hosted voice-agent platform. -
4
Grok Voice 3.0
SpaceXSI
Grok Voice 3.0 is a speech-to-speech model offered through the Grok Voice Agent API for developers building real-time voice applications. It accepts audio and text and returns spoken audio or text through a WebSocket session, supporting conversational turn-taking, interruptions, and function calling. Developers can connect the model to custom functions and server-side tools, including web search, X search, collections, and remote MCP servers. The API is intended for interactive voice agents such as customer-support and service-call experiences, and is also used for voice interactions in Tesla vehicles and Grok Bot. Billing is usage-based, with audio charged per minute and text input events billed separately. The API documentation includes setup instructions and examples for Python and JavaScript clients.Starting Price: $0.08/min -
5
Leadlock
Leadlock
Leadlock is a speech-to-speech voice AI platform built specifically for GoHighLevel agencies, helping them answer every call, qualify leads, book appointments, and update GHL pipelines in real time. Unlike traditional voice AI stacks that chain speech-to-text, an LLM, and text-to-speech, it supports true multimodal speech-to-speech through OpenAI Realtime and Gemini Live, alongside xAI Grok and ElevenLabs options, enabling sub-second latency, natural turn-taking, and interruptions. Agencies can choose from more than 72 voices across multiple providers and select different models for different agents and use cases. Native GoHighLevel integration connects contacts, calendars, pipelines, opportunities, tags, custom fields, workflows, and sub-accounts without middleware or Zapier-style glue. Before answering, agents can pull caller history and CRM context to personalize conversations from the first ring.Starting Price: $97 per month -
6
MiniMax Speech 2.8
MiniMax
MiniMax Speech 2.8 is a next-generation AI speech model built to make synthetic voice feel alive, expressive, and deeply human. It focuses on performance in real-world voice agent scenarios, combining ultra-fast response, richer emotional expression, cleaner audio, and stronger cross-lingual performance for products that need natural spoken interaction. Speech 2.8 is designed to reduce the distance between AI voice and real human communication, giving developers and creators more control over how a voice sounds, reacts, and carries meaning. It supports flexible emotion control, allowing users to shape delivery with moods, tone, and expressive direction instead of relying on flat or robotic speech. It can produce speech with more natural pauses, cadence, emphasis, and emotional texture, helping AI characters, assistants, narrators, and interactive agents sound more believable across longer conversations. -
7
Cartesia Sonic-3
Cartesia
Cartesia Sonic-3 is a real-time, streaming text-to-speech (TTS) model designed to generate ultra-realistic, expressive voice output with extremely low latency, enabling AI systems to speak as fluidly as humans in live interactions. Built on advanced state space model architecture, Sonic delivers high-quality speech while achieving near-instant response times, with audio generation beginning in as little as 40–100 milliseconds, making conversations feel seamless rather than delayed. It is optimized for conversational AI use cases, acting as the “voice layer” for AI agents by converting text into natural-sounding speech that includes emotional nuance such as excitement, empathy, or even laughter. It supports more than 40 languages with native-level voices and accent localization, allowing developers to build globally accessible applications with consistent quality across regions.Starting Price: $4 per month -
8
Voxtral Mini TTS 3.0
Mistral AI
Voxtral Mini TTS 3.0 is Mistral AI's text-to-speech model for developers building voice-enabled applications and services. It generates speech from text in batch and real-time workflows, with preset or cloned voices, emotion and pace controls, and custom pronunciation. The model supports multilingual speech generation and dialect adaptation, making it suitable for conversational audio, localized content, spoken responses, and voice agents. Developers can access speech generation and voice-cloning capabilities through Mistral's API. Voxtral Mini TTS 3.0 is also part of Mistral's Voxtral 3 voice-agent stack, which combines speech recognition, reasoning, tool use, and generated speech; the Voxtral 3 stack can be self-deployed on customer infrastructure.Starting Price: $13/1M chars -
9
Google has released updated Gemini audio models that significantly expand the platform’s capabilities for natural, expressive voice interactions and real-time conversational AI with the introduction of Gemini 2.5 Flash Native Audio and improved text-to-speech technology. The updated native audio model powers live voice agents that can handle complex workflows, follow detailed user instructions more reliably, and maintain smoother multi-turn conversations by better recalling context from previous turns. It is now available across Google AI Studio,Gemini Enterprise Agent Platform, Gemini Live, and Search Live, enabling developers and products to build interactive voice experiences such as intelligent assistants and enterprise voice agents. In addition to the real-time voice improvements, Google enhanced the underlying Text-to-Speech (TTS) models in the Gemini 2.5 family to offer greater expressivity, tone control, pacing adjustments, and multilingual support.
-
10
MAI-Voice-2.1
Microsoft
MAI-Voice-2.1 is Microsoft's hosted text-to-speech model for developers building voice-enabled products. It generates expressive speech from text, supports multilingual output across 23 languages, and offers emotion and style controls, long-form speaker consistency, and gated matching to consented reference voices. Developers access it through Microsoft Foundry and Azure Speech APIs and SDKs for narration, audiobooks, voice assistants, and customer-service experiences.Starting Price: $22/1M characters -
11
Gemini 2.5 Flash TTS
Google
Gemini 2.5 Flash TTS is the latest text-to-speech (TTS) model variant in Google’s Gemini 2.5 lineup, designed for faster, low-latency speech synthesis with expressive, controllable audio output. It offers significant enhancements in tone versatility and expressivity so that developers can generate speech that better matches style prompts, from storytelling narrations to character voices, with more natural emotional range. It features precision pacing, which allows it to adjust speech tempo based on context, delivering faster sections or slowing for emphasis more accurately according to instructions. It also supports multi-speaker dialogues with consistent character voices for scenarios like podcasts, interviews, or conversational agents, and improved multilingual handling so each speaker’s unique tone and style persist across languages. Gemini 2.5 Flash TTS is optimized for lower latency, making it ideal for interactive applications and real-time voice interfaces. -
12
Vision Agents
Stream
Vision Agents is an open source Python framework for building low-latency voice and video AI agents with any model. It lets developers plug in LLM, speech, and vision models from more than 25 providers and ship real-time agents for telehealth, voice support, live coaching, video analysis, interactive avatars, security monitoring, sports commentary, and other multimodal applications. It is designed to help teams build agents that can listen, speak, see, process media, call tools, and respond in real time while running on Stream’s global edge network with sub-500ms latency. Developers can build a first agent in minutes, using a small Python setup with Gemini Realtime, OpenAI, Deepgram, ElevenLabs, Stream, or other supported providers. Vision Agents supports both real-time speech-to-speech models and custom STT/LLM/TTS pipelines, giving teams either the fastest path to a working voice agent or full control over speech recognition, language reasoning, text-to-speech, etc.Starting Price: Free -
13
Gemini 3.8 Flash-Lite TTS
Google
Gemini 3.8 Flash-Lite TTS is Google’s cost-efficient text-to-speech model designed for high-volume dubbing, audio production, and expressive voice-agent applications. The model provides fine-grained control over tone, pacing, expressive nuance, and line-by-line vocal delivery. It supports long-form speech generation while maintaining natural pacing, voice quality, and speaker consistency across extended content. Native two-speaker scene staging enables multi-turn dialogue with distinct voices and natural conversational turn-taking from a single script. Gemini 3.8 Flash-Lite TTS supports more than 100 languages and can add nonverbal cues and backchanneling to create more natural conversational audio. The model is available through the Gemini API and Google AI Studio, with deployment through Google Vids and planned enterprise availability through Gemini Enterprise. -
14
Voxtral Mini Transcribe 3
Mistral AI
Voxtral Mini Transcribe 3 is a speech-to-text model from Mistral AI that converts audio recordings into written transcripts through an API. Developers can submit audio for batch transcription and receive text with timestamps and speaker labels. It supports multilingual transcription, speaker diarization, and context biasing, which lets an application supply names or specialized vocabulary to guide recognition. The model is designed for developers building applications and audio workflows that need to make recorded speech searchable, attribute words to speakers, or align transcript segments with audio. Teams can call it through Mistral's hosted API and incorporate its output into their own software, such as transcription pipelines and voice-enabled services. It is a model/API offering rather than a standalone recording or editing application.Starting Price: $0.0035/min -
15
MAI-Voice-2-Flash
Microsoft
MAI-Voice-2-Flash is Microsoft AI’s fast, efficient text-to-speech model for high-volume voice experiences where responsiveness is essential. It produces high-fidelity, natural, and expressive speech while preserving the prosody, acoustic quality, human-like rhythm, intonation, and emotional nuance of MAI-Voice-2. The model is optimized for real-time synthesis and runs twice as fast as MAI-Voice-2, making it suitable for voice agents, assistants, interactive applications, call centers, and IVR systems that must respond without noticeable delay. It supports 15 languages across 18 locales and includes a library of licensed, curated voices that can be used immediately. Developers can control speaking style and emotion through SSML, shaping delivery with expressions such as joy, excitement, empathy, sadness, whispering, or shouting to match different conversational situations and brand experiences. -
16
Inworld TTS
Inworld
Inworld TTS is a state-of-the-art text-to-speech platform designed to deliver ultra-realistic, context-aware speech synthesis and precise voice-cloning capabilities at a radically accessible price. The flagship model, TTS-1, is optimized for real-time applications and supports low-latency streaming (first audio chunk in ≈200 ms) as well as multiple languages (including English, Spanish, French, Korean, Chinese, and more). Developers can use instant zero-shot voice cloning (5-15 seconds of audio) or professional fine-tuned cloning, add voice-tags for emotion, style, and non-verbal sounds, and switch languages while preserving voice identity. The larger TTS-1-Max model (in preview) offers even more expressive speech and multilingual strength. The platform supports both API and portal access, streaming or batch mode, and is designed for everything from interactive voice agents and gaming characters to branded audio experiences.Starting Price: $0.005 per minute -
17
OpenAI Realtime API
OpenAI
The OpenAI Realtime API is a newly introduced API, announced in 2024, that allows developers to create applications that facilitate real-time, low-latency interactions, such as speech-to-speech conversations. This API is designed for use cases like customer support agents, AI voice assistants, and language learning apps. Unlike previous implementations that required multiple models for speech recognition and text-to-speech conversion, the Realtime API handles these processes seamlessly in one call, enabling applications to handle voice interactions much faster and with more natural flow. -
18
aiOla
aiOla
aiOla is a deep tech Conversational, Voice, and Speech AI lab with an enterprise-level automatic speech recognition (ASR) foundation model, Text-to-speech (TTS) technology and Natural Language Understanding (NLU). It’s designed to help enterprises and developers adapt speech technologies to any process, whether through seamless API integration or an intuitive in-house app. aiOla is revolutionizing enterprise operations with enterprise level Conversational AI. We specialize in speech-to-text and text-to-speech AI that deliver unmatched accuracy (95%), specialized in specific jargon, in any language, accent, vertical, or acoustic environment. From empowering frontline workers with hands-free workflows to enabling voice AI agents with enterprise-grade ASR and TTS, aiOla seamlessly integrates into workflows, internal apps and products. -
19
Voxtral Mini Transcribe Realtime 3
Mistral AI
Voxtral Mini Transcribe Realtime 3 is a speech-to-text model delivered through Mistral’s API for applications that need live transcription. It streams audio over WebSocket and returns transcript events while a person is speaking, with configurable streaming delays. Developers can use it to add real-time captions, voice-assistant input, or transcription to voice-agent workflows. The model provides turn detection, speaker diarization, and context biasing for domain-specific vocabulary, and supports transcription across 45 languages and dialects. Applications can connect to its real-time endpoint and receive transcription events as audio arrives, rather than waiting for an entire recording to finish. Voxtral Mini Transcribe Realtime 3 is part of Mistral’s Voxtral audio model family.Starting Price: $0.008/min -
20
ElevenLabs
ElevenLabs
The most realistic and versatile AI speech software, ever. Eleven brings the most compelling, rich and lifelike voices to creators and publishers seeking the ultimate tools for storytelling. Generate top-quality spoken audio in any voice and style with the most advanced and multipurpose AI speech tool out there. Our deep learning model renders human intonation and inflections with unprecedented fidelity and adjusts delivery based on context. Our AI model is built to grasp the logic and emotions behind words. And rather than generate sentences one-by-one, it’s always mindful of how each utterance ties to preceding and succeeding text. This zoomed-out perspective allows it to intonate longer fragments convincingly and with purpose. And finally you can do this with any voice you want.Starting Price: $1 per month -
21
Cartesia Sonic-3.5
Cartesia
Sonic 3.5 is Cartesia’s fastest, most natural text-to-speech model, built for expressive, real-time voice generation with sub-90ms latency and native support for 42 languages. It is designed to follow transcripts faithfully, voice confirmation codes, and heteronyms correctly without preprocessing, and stay expressive enough to carry a real conversation. It supports languages intended to deliver native-quality speech. Sonic 3.5 focuses on clean audio across every language and voice, with no artifacts to edit out, making it practical for production voice experiences where quality, speed, and consistency matter. Its expressive conversational delivery provides strong pacing and real emotional range, tuned for support and agent transcripts. Alphanumerics such as order numbers, phone numbers, IDs, and emails are spoken naturally in every language, while context-aware English pronunciation helps words like read, bass, and bow land correctly from the surrounding text. -
22
Dograh
Dograh
Dograh is an open source, self-hostable voice agent platform with a no-code workflow builder for creating production voice agents. Teams can choose their own inbound channels, speech-to-text, LLM, text-to-speech, and telephony providers, or replace the traditional cascade with speech-to-speech models for direct audio-in, audio-out conversations with natural turn-taking, interruption handling, and low latency. The platform supports inbound and outbound calling, widgets, telephony integrations, observability, traces, real-time analytics, hybrid pre-recorded voice plus TTS, and more than 70 languages. Its MCP server lets Claude Code, Cursor, OpenClaw, Codex, and other agent runtimes create, modify, and deploy voice agents directly from development environments. Dograh can run on your own servers, inside a private cloud or VPC, or in a managed environment, with support for models hosted entirely within your perimeter.Starting Price: 1¢ per minute -
23
Miso TTS
Miso TTS
Miso Labs builds emotive foundation models for voice, designed to help developers create voice agents that feel fast, warm, and human instead of robotic or delayed. Its flagship model, Miso TTS, is an 8-billion-parameter transformer model for state-of-the-art emotive speech and dialogue generation, with open source weights available on Hugging Face and API access coming soon. Miso is built for real-time conversational voice, responding in 110ms to preserve natural flow and avoid the awkward pauses common in AI voice agents. It supports one-shot voice cloning, allowing users to clone a voice from a ten-second audio clip while keeping the agent’s voice consistent from the first second of a call to the last. Miso Labs also emphasizes local and sovereign deployment, with open source models built for local use and on-premises hosting and support available for enterprise teams that need to keep sensitive data in-house. -
24
Grok Text to Speech (TTS)
SpaceXSI
Grok Text to Speech (TTS) is a standalone audio API built to help developers generate fast, natural, and expressive speech from text. Built on the same stack that powers Grok Voice, Tesla vehicles, and Starlink customer support, the API makes it straightforward to integrate high-quality voice generation into applications such as voice agents, accessibility tools, podcasts, assistants, customer experiences, and interactive audio products. Grok TTS can turn long-form text into speech through a REST API or generate speech in real time through a WebSocket API, giving developers flexibility for both batch audio generation and live conversational experiences. It is designed around expressive delivery, not just flat narration, with fine-grained control through simple inline and wrapping speech tags. Developers can add natural prosody and emotion using tags, allowing lifelike delivery without complex markup. -
25
Gemini 3.8 Flash TTS
Google
Gemini 3.8 Flash TTS is Google’s expressive text-to-speech model for creating custom voices, directed performances, and multilingual audio experiences. The model can generate original voices from natural-language prompts by specifying characteristics such as role, accent, tone, pacing, and vocal style across more than 100 languages and dialects. Users can also replicate an authorized voice from a short audio sample, with consent verification, SynthID watermarking, and C2PA credentials supporting responsible voice creation. Gemini 3.8 Flash TTS provides line-by-line performance control, long-form speech generation, two-speaker scene staging, and support for nonverbal cues such as laughs, sighs, gasps, and conversational backchanneling. It is suited to use cases including games, audiobooks, podcasts, dubbing, interactive voice agents, branded audio, and media localization. -
26
Gradium
Gradium
Gradium is a voice AI platform for developers and organizations building speech-enabled applications and conversational agents. Its hosted APIs provide streaming text-to-speech, speech-to-text, speech translation, and speech-to-speech, with WebSocket and REST interfaces, real-time turn detection, pronunciation controls, and voice design or cloning features. A browser-based studio lets users try the models and manage voices, while documentation and SDK guides support application development. Use cases include voice agents, customer-service automation, live transcription, multilingual voice experiences, and spoken content generation. Gradium also publishes Phonon, an open-weight text-to-speech model designed for local, offline use in applications and on-device systems. Plans use credits for speech generation, transcription, and translation.Starting Price: $0/month -
27
Grok Speech to Text (STT)
SpaceXSI
Grok Speech to Text is a standalone audio API built to help developers integrate fast, accurate transcription into any application. Built on the same stack that powers Grok Voice, Tesla vehicles, and Starlink customer support, the API is designed for use cases such as voice agents, real-time transcription tools, accessibility solutions, podcasts, meeting capture, telephony, and interactive audio experiences. Grok STT can generate transcripts from large audio files through a REST API or transcribe speech in real time through a low-latency WebSocket API. It includes word-level timestamps, speaker diarization, multichannel support, and intelligent Inverse Text Normalization that converts spoken language into properly formatted structured output for numbers, dates, currencies, and more. Grok Speech to Text is evaluated across phone calls, meetings, video and podcast content, and telephony, with strong performance in entity recognition and business use cases. -
28
Qwen3-TTS
Alibaba
Qwen3-TTS is an open source series of advanced text-to-speech models developed by the Qwen team at Alibaba Cloud under the Apache-2.0 license, offering stable, expressive, and real-time speech generation with features such as voice cloning, voice design, and fine-grained control of prosody and acoustic attributes. The models support 10 major languages, including Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian, and multiple dialectal voice profiles with adaptive control over tone, speaking rate, and emotional expression based on text semantics and instructions. Qwen3-TTS uses efficient tokenization and a dual-track architecture that enables ultra-low-latency streaming synthesis (first audio packet in ~97 ms), making it suitable for interactive and real-time use cases, and includes a range of models with different capabilities (e.g., rapid 3-second voice cloning, custom voice timbres, and instruction-based voice design).Starting Price: Free -
29
Cartesia Sonic-3.6
Cartesia
Sonic is a real-time text-to-speech model built for voice agents, combining natural delivery, sub-90ms latency, and native support for more than 40 languages. It is designed to make voice interactions feel effortless, with tone that adjusts to context, consistent pacing, and speech that follows the natural rhythm of conversation. By default, Sonic interprets the emotional subtext of a transcript and calibrates delivery automatically, while non-verbal expressions such as laughter can be inserted directly into the text. The model follows transcripts faithfully, produces clean audio across languages and voices, and handles alphanumeric content such as order numbers, phone numbers, IDs, and email addresses naturally without preprocessing. Context-aware pronunciation helps heteronyms sound correct from surrounding words, while custom pronunciation dictionaries let teams define how proper nouns and domain-specific terms should be spoken.Starting Price: $5 per month -
30
Higgs Realtime
Boson AI
Higgs Realtime is a production-quality, real-time speech-to-speech model and API built for natural, continuous conversation. It is an end-to-end, instruction-tuned, audio-native model that can understand audio, text, or both and generate high-quality responses, while also functioning as a text LLM when given text alone. Designed for live voice agents, it follows conversations, handles interruptions, adapts when requests change mid-sentence, and carries multi-step workflows through to completion. The model is trained specifically for voice-agent reflexes such as natural turn-taking, conversational cadence, tone adaptation, spoken tool preambles, multi-turn state tracking, and robust instruction following through changing requests. Semantic turn detection helps distinguish a completed turn from a pause, while multilingual and code-switched understanding supports more than 100 languages without per-language setup.Starting Price: $0.0023 per minute -
31
KugelAudio
KugelAudio
KugelAudio is the most realistic speech AI platform, combining text-to-speech, speech-to-text, and voice-to-voice in one stack. With 39-50ms inference latency (lowest on the market), 30-second voice cloning, on-premises deployment, and industry-leading accuracy on email addresses, IBANs, and phone numbers, it's built for production voice applications where quality and compliance matter. It's a strong fit for voice bots and conversational agents that need to handle structured data without misreads, real-time applications requiring sub-50ms latency, and regulated industries like banking, insurance, healthcare, and the public sector that need on-premises or EU-sovereign deployment. Beyond enterprise voice automation, KugelAudio also powers branded voice experiences through natural cloning from 30 seconds of audio, multilingual products across over 30 languages German, English, French, and Italian, and media or content production needing the most realistic synthetic voices available.Starting Price: $1 -
32
Gemini 2.5 Pro TTS
Google
Gemini 2.5 Pro TTS is Google’s advanced text-to-speech model in the Gemini 2.5 family, optimized for high-quality, expressive, controllable speech synthesis for structured and professional audio generation tasks. The model delivers natural-sounding voice output with enhanced expressivity, tone control, pacing, and pronunciation fidelity, enabling developers to dictate style, accent, rhythm, and emotional nuance through text-based prompts, making it suitable for applications like podcasts, audiobooks, customer assistance, tutorials, and multimedia narration that require premium audio output. It supports both single-speaker and multi-speaker audio, allowing distinct voices and conversational flows in the same output, and can synthesize speech across multiple languages with consistent style adherence. Compared with lower-latency variants like Flash TTS, the Pro TTS model prioritizes sound quality, depth of expression, and nuanced control. -
33
Grok Voice Think Fast 1.0
SpaceXSI
Grok Voice Think Fast 1.0 is an advanced voice AI model developed by xAI, designed to handle complex, real-world conversational workflows. It excels in multi-step tasks across customer support, sales, and enterprise applications. The model is built for fast, natural conversations while maintaining high accuracy and responsiveness. It supports real-time reasoning without adding latency, allowing it to process and respond intelligently during live interactions. Grok Voice can accurately capture and confirm structured data such as names, addresses, and account details, even in noisy or challenging conditions. It is optimized for global use with support for over 25 languages. The model is capable of handling interruptions, accents, and ambiguous inputs with ease. Overall, it enables businesses to deploy efficient, scalable voice agents for high-volume interactions. -
34
Realtime TTS-2
Inworld
Realtime TTS-2 from Inworld AI is a new generation of voice model built for real-time conversation: a voice model that feels as human as it sounds. It hears the full audio of an exchange, picks up the user’s tone, pacing, and emotional state, then takes voice direction in plain English, the way developers prompt an LLM. Instead of generating speech in isolation, it listens to prior turns of the exchange, so tone and pacing carry forward, and the same line can land differently after a joke than after bad news. Voice Direction lets developers steer delivery like a director would steer a voice actor, using natural-language descriptions rather than fixed emotion presets or sliders. Inline nonverbals like [sigh], [breathe], and [laugh] can be placed inside the text, and the model renders them as audio events. Realtime TTS-2 preserves one voice identity across more than 100 languages, including mid-utterance language switches.Starting Price: $25 per month -
35
MARS6
CAMB.AI
CAMB.AI's MARS6 is a groundbreaking text-to-speech (TTS) model that has become the first speech model accessible on Amazon Web Services (AWS) Bedrock platform. This integration allows developers to incorporate advanced TTS capabilities into generative AI applications, facilitating the creation of enhanced voice assistants, engaging audiobooks, interactive media, and various audio-centric experiences. MARS6's advanced algorithms enable natural and expressive speech synthesis, setting a new standard for TTS conversion. Developers can access MARS6 directly through the Amazon Bedrock platform, ensuring seamless integration into applications and enhancing user engagement and accessibility. The inclusion of MARS6 in AWS Bedrock's diverse selection of foundation models underscores CAMB.AI's commitment to advancing machine learning and artificial intelligence, providing developers with vital tools to create rich audio experiences supported by AWS's reliable and scalable infrastructure. -
36
Cartesia Ink-Whisper
Cartesia
Cartesia Ink is a family of real-time streaming speech-to-text (STT) models designed to power fast, natural conversations in voice AI applications, acting as the “voice input” layer that converts spoken language into accurate text instantly. Its flagship model, Ink-Whisper, is specifically engineered for conversational environments, delivering ultra-low latency transcription with a time-to-complete-transcript as fast as 66 milliseconds, enabling fluid, human-like interactions without noticeable delays. Unlike traditional transcription systems built for batch processing, Ink is optimized for live dialogue, handling fragmented, variable-length audio through dynamic chunking, which reduces errors and improves responsiveness during pauses, interruptions, or rapid exchanges.Starting Price: $4 per month -
37
Grok Voice Think Fast 2.0
SpaceXSI
Grok Voice Think Fast 2.0 is xAI’s flagship voice model for building real-time assistants, phone agents, and interactive voice systems that stream audio and text bidirectionally over WebSocket. Developers can configure system instructions, high or no reasoning effort, built-in or custom voices, automatic server-side voice activity detection, silence duration, idle re-engagement, playback speed, and session resumption after temporary disconnects. It accepts PCM, G.711 μ-law, G.711 A-law, and Opus audio through JSON or raw binary frames, with configurable PCM sample rates from telephone quality to 48 kHz. It supports more than 20 languages with native-quality accents, automatic language detection, natural responses in the speaker’s language, and seamless code-switching. Language hints and up to 100 key terms improve transcription of regional speech, names, products, codes, addresses, and specialized terminology, while pronunciation replacements correct spoken output. -
38
Azure Voice Live API
Microsoft
Azure Voice Live API is a fully managed solution for building low-latency, high-quality speech-to-speech agents through one unified interface. It combines speech recognition, generative AI, and text-to-speech, allowing developers to send audio input and receive audio output, synchronized avatar visuals, and action triggers without manually orchestrating separate backend components or deploying the underlying models. It supports more than 140 speech-to-text locales and over 600 standard voices across 150+ text-to-speech locales, with options for phrase lists, custom speech, custom voices, and brand-aligned avatars. Developers can choose among multiple generative AI models, including GPT-Realtime, GPT-5, GPT-4.1, GPT-4o, Phi, and compatible bring-your-own models, depending on the intelligence, speed, and latency required. Advanced conversational features include noise suppression, echo cancellation, robust interruption detection, and end-of-turn detection. -
39
Gemini 3.1 Flash TTS
Google
Gemini 3.1 Flash TTS is Google’s latest text-to-speech model designed to deliver highly expressive, controllable, and scalable AI-generated speech for developers and enterprises. Available in Google AI Studio and Gemini Enterprise Agent Platform, it focuses on precise control over how audio is generated, allowing users to shape delivery through natural language prompts and an extensive system of more than 200 audio tags that define pacing, tone, emotion, and style. It supports over 70 languages and regional variants, along with a library of 30 prebuilt voices, enabling users to generate speech ranging from professional narration to conversational or stylized performances. Developers can embed instructions directly into text inputs to guide vocal expression, combining pacing, emotion, and pauses in a structured prompting framework that produces nuanced, high-fidelity audio output. Gemini 3.1 Flash TTS is optimized for real-world applications. -
40
Boson AI
Boson AI
Boson AI provides voice agents powered by foundation audio models, built to run in business workflows and learn from every call. Higgs Realtime enables live voice agents for support lines, sales calls, and product assistants that listen, reason, call tools, and respond in real time with low latency and natural speech-to-speech interaction. Higgs Audio and Avatar extend these capabilities with text-to-speech, speech-to-text, voice cloning, sentiment detection, and avatar generation, producing natural speech while understanding tone, emotion, and intent. The models support high-accuracy multilingual speech recognition, real-time translation, and expressive voice generation, while sentiment signals can improve routing, analytics, and context-aware agent behavior. Designed for real-world production, the platform emphasizes quality, latency, reliability, and flexible deployment across managed and self-serve environments. -
41
ElevenAgents
ElevenLabs
ElevenLabs Agents is a platform for building, deploying, and scaling intelligent conversational AI agents that can speak, type, and take action across phone, web, and application environments. It enables developers and teams to create real-time agents that interact naturally with users through voice and text, combining speech-to-text, large language models, and text-to-speech into a unified system that functions like a human conversation partner. It allows agents to resolve customer issues, automate workflows, answer questions, and execute tasks based on connected data sources and predefined logic, making interactions both accurate and context-aware. These agents can be customized with knowledge bases, system prompts, and tools that enable them to access external systems, execute custom logic, and perform actions beyond simple responses. They support multimodal capabilities, meaning they can read, speak, and interpret inputs while handling conversational dynamics.Starting Price: $5 per month -
42
Gemini 3.8 Live
Google
Gemini 3.8 Live is Google DeepMind’s real-time speech-to-speech AI model for building conversational voice applications and interactive agents. The model can maintain natural dialogue while reasoning, using tools, and carrying out tasks during an ongoing conversation. Asynchronous function calling allows applications to execute API and tool requests in the background while Gemini continues streaming audio responses to the user. Gemini 3.8 Live can also incorporate live visual context, enabling agents to respond based on what users say and what the system can see. It supports more than 97 languages, maintains accent consistency, and is designed to accurately interpret alphanumeric information such as confirmation codes, claim numbers, and technical data. Gemini 3.8 Live is available through the Gemini Live API and Google AI Studio for developers building customer service agents, assistants, training applications, and other voice-first experiences. -
43
GPT‑Realtime‑Whisper
OpenAI
GPT-Realtime-Whisper is OpenAI’s streaming transcription model built for low-latency speech-to-text experiences in live products. It transcribes audio as people speak, helping voice-enabled apps feel faster, more responsive, and more natural, from captions that appear in the moment to meeting notes that keep up with the conversation. It makes live speech usable inside business workflows as it happens, so teams can power captions for meetings, classrooms, broadcasts, and events, generate notes and summaries while conversations are still in progress, build voice agents that need to understand users continuously, and create faster follow-up workflows for high-volume spoken interactions. It is part of a new generation of real-time voice models in the API that can reason, translate, and transcribe as people speak, moving real-time audio beyond simple call-and-response toward voice interfaces that can listen, translate, transcribe, and take action as a conversation unfolds.Starting Price: $0.017 per minute -
44
gpt-4o-mini Realtime
OpenAI
The gpt-4o-mini-realtime-preview model is a compact, lower-cost, realtime variant of GPT-4o designed to power speech and text interactions with low latency. It supports both text and audio inputs and outputs, enabling “speech in, speech out” conversational experiences via a persistent WebSocket or WebRTC connection. Unlike larger GPT-4o models, it currently does not support image or structured output modalities, focusing strictly on real-time voice/text use cases. Developers can open a real-time session via the /realtime/sessions endpoint to obtain an ephemeral key, then stream user audio (or text) and receive responses in real time over the same connection. The model is part of the early preview family (version 2024-12-17), intended primarily for testing and feedback rather than full production loads. Usage is subject to rate limits and may evolve during the preview period. Because it is multimodal in audio/text only, it enables use cases such as conversational voice agents.Starting Price: $0.60 per input -
45
Amazon Nova 2 Sonic
Amazon
Nova 2 Sonic is Amazon’s real-time speech-to-speech model designed to deliver natural, flowing voice interactions without relying on separate systems for text and audio. It combines speech recognition, speech generation, and text processing in a single model, enabling smooth, human-like conversations that can shift effortlessly between voice and text. With expanded multilingual support and expressive voice options, it produces responses that sound more lifelike and contextually aware. Its one-million-token context window allows for long, continuous interactions without losing track of prior details. It supports asynchronous task handling, meaning users can continue speaking, change topics, or ask follow-up questions while background tasks, such as searching for information or completing a request, continue uninterrupted. This makes voice experiences feel more fluid and less bound by traditional turn-based dialog constraints. -
46
Octave TTS
Hume AI
Hume AI has introduced Octave (Omni-capable Text and Voice Engine), a groundbreaking text-to-speech system that leverages large language model technology to understand and interpret the context of words, enabling it to generate speech with appropriate emotions, rhythm, and cadence, unlike traditional TTS models that merely read text, Octave acts akin to a human actor, delivering lines with nuanced expression based on the content. Users can create diverse AI voices by providing descriptive prompts, such as "a sarcastic medieval peasant," allowing for tailored voice generation that aligns with specific character traits or scenarios. Additionally, Octave offers the flexibility to modify the emotional delivery and speaking style through natural language instructions, enabling commands like "sound more enthusiastic" or "whisper fearfully" to fine-tune the output.Starting Price: $3 per month -
47
Voxtral TTS
Mistral AI
Voxtral TTS is a state-of-the-art, multilingual text-to-speech model designed to generate highly realistic and emotionally expressive speech from text, combining strong contextual understanding with advanced speaker modeling to produce natural, human-like audio output. Built as a lightweight model with around 4 billion parameters, it delivers efficient performance while maintaining high quality, enabling scalable deployment for enterprise voice applications. It supports nine major languages and diverse dialects, and can adapt to new voices using only a short reference audio sample, capturing not just tone but also rhythm, pauses, intonation, and emotional nuance. Its zero-shot voice cloning capabilities allow it to replicate a speaker’s style without additional training, and it can even perform cross-lingual voice adaptation, generating speech in one language while preserving the accent of another. -
48
Amazon Nova Sonic
Amazon
Amazon Nova Sonic is a state-of-the-art speech-to-speech model that delivers real-time, human-like voice conversations with industry-leading price performance. It unifies speech understanding and generation into a single model, enabling developers to create natural, expressive conversational AI experiences with low latency. Nova Sonic adapts its responses based on the prosody of input speech, such as pace and timbre, resulting in more natural dialogue. It supports function calling and agentic workflows to interact with external services and APIs, including knowledge grounding with enterprise data using Retrieval-Augmented Generation (RAG). It provides robust speech understanding for American and British English across various speaking styles and acoustic conditions, with additional languages coming soon. Nova Sonic handles user interruptions gracefully without dropping conversational context and is robust to background noise. -
49
Qwen-Audio-3.0-TTS-Flash
Alibaba
Qwen-Audio-3.0-TTS-Flash is the real-time variant of Qwen-Audio-3.0-TTS, tuned for interactive applications with first-packet latency at the 300 ms level. It supports 16 languages, along with improved fidelity for several Chinese dialects. Across multilingual evaluations, Flash delivers the lowest average WER/CER in the family at 3.87, showing strong intelligibility while preserving speaker identity across diverse languages. Developers can guide delivery with plain-language instructions instead of manually adjusting acoustic parameters, controlling emotion, role, scenario, pace, projection, and tone through simple prompts. Inline tags add precise non-verbal details, making the model well-suited to conversational agents, narration, games, dubbing, and other expressive speech experiences. Voice cloning is designed to work with imperfect reference audio; targeted acoustic simulation suppresses noise and reverberation while retaining the original speaker’s timbre. -
50
VaxVoIP Agent AI SDK
VaxSoft
VaxVoIP Agent AI SDK is a Windows software development kit for connecting SIP servers and IP-PBX systems to OpenAI Realtime speech-to-speech models. It bridges live SIP call audio with AI so developers can build multilingual telephone agents and commercial voice applications without implementing the low-level telephony and model connection themselves. The SDK includes technical documentation and sample projects for Visual C# .NET, Visual Basic .NET and Delphi. Supported use cases include AI receptionists, customer service and information agents, outbound voice agents, and smart IVR applications. It is intended for developers, VoIP providers and businesses creating voice-agent solutions for existing telephony environments. A 30-day functional trial is offered; commercial licenses are sold annually by call capacity and service scope.Starting Price: $1,480/year
