The request is for text-to-speech for "Shanghai Guide", which is a generic TTS need; the sources show several products that convert text to speech. ElevenLabs offers a voice generator with 17,500+ voices and APIs/SDKs 15, Replicate runs MiniMax speech-02-hd for text-to-audio synthesis 26, LocalAI offers a text-to-speech action on self-hosted hardware 37, and Deepgram provides TTS via a batch speak endpoint 48.
- 1
ElevenLabselevenlabs.ioverified and signed
Converts text to lifelike speech with 17,500+ voices in 90+ languages, reachable through its APIs, SDKs and an MCP server 15.
official:MCP server · ElevenLabs+58 community tools built for it
for agents: elevenlabs-text-to-speech · text_to_speech · text-to-speech
- 2
- 3
- 4
Sources
- 1Free AI Voice Generator & Voice Agents Platform | ElevenLabselevenlabs.io · read 2026-10-29
- 2Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 3LocalAI · Make AI run on every machinelocalai.io · read 2026-10-29
- 4Enterprise voice AI: STT, TTS & agent APIs | Deepgramdeepgram.com · read 2026-10-29
- 5ElevenLabs (Activepieces): declares "elevenlabs-text-to-speech" (the record we read and signed)unfragile.ai · read 2026-10-24
- 6minimax/speech-02-hd: declares "minimax/speech-02-hd" (the record we read and signed)unfragile.ai · read 2026-10-24
- 7LocalAI (Activepieces): declares "text_to_speech" (the record we read and signed)unfragile.ai · read 2026-10-24
- 8Deepgram (Activepieces): declares "text_to_speech" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
elevenlabs-text-to-speech · ElevenLabs (Activepieces) verified and signed
Text to Speech — Convert text to speech using Elevenlabs
minimax/speech-02-hd · minimax/speech-02-hd verified and signed
Text-to-Audio (T2A) that offers voice synthesis, emotional expression, and multilingual capabilities. Optimized for high-fidelity applications like voiceovers and audiobooks.
jaaari/kokoro-82m · jaaari/kokoro-82m verified and signed
Kokoro v1.0 - text-to-speech (82M params, based on StyleTTS2)
minimax/speech-02-turbo · minimax/speech-02-turbo verified and signed
Text-to-Audio (T2A) that offers voice synthesis, emotional expression, and multilingual capabilities. Designed for real-time applications with low latency
minimax/speech-2.6-hd · minimax/speech-2.6-hd verified and signed
MiniMax Speech 2.6 HD delivers studio-quality multilingual text-to-audio on Replicate with nuanced prosody, subtitle export, and premium voices
xai/grok-text-to-speech · xai/grok-text-to-speech verified and signed
Convert text to natural-sounding speech with xAI's Grok TTS. 5 voices, 20 languages, expressive speech tags, and high-fidelity MP3 / WAV / telephony audio output.
adirik/styletts2 · adirik/styletts2 verified and signed
Generates speech from text
inworld/realtime-tts-1.5-max · inworld/realtime-tts-1.5-max verified and signed
Highest-quality realtime text-to-speech with <200ms latency, emotion control, and 15-language support
openai/whisper · openai/whisper verified and signed
Convert speech in audio to text
alphanumericuser/kokoro-82m · alphanumericuser/kokoro-82m verified and signed
Kokoro v1.0 - text-to-speech (82M params, based on StyleTTS2)
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.